End of training
Browse files- README.md +100 -0
- all_results.json +22 -0
- config.json +42 -0
- eval_results.json +17 -0
- model.safetensors +3 -0
- preprocessor_config.json +23 -0
- runs/Feb03_18-39-25_modal/events.out.tfevents.1738607969.modal.2.0 +3 -0
- runs/Feb03_18-39-25_modal/events.out.tfevents.1738607969.modal.2.1 +3 -0
- runs/Feb03_18-39-25_modal/events.out.tfevents.1738608289.modal.2.2 +3 -0
- runs/Feb03_18-39-25_modal/events.out.tfevents.1738608289.modal.2.3 +3 -0
- train_results.json +8 -0
- trainer_state.json +2157 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: google/vit-base-patch16-224
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: square_run_32_batch
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# square_run_32_batch
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.6241
|
| 22 |
+
- F1 Macro: 0.5019
|
| 23 |
+
- F1 Micro: 0.5758
|
| 24 |
+
- F1 Weighted: 0.5679
|
| 25 |
+
- Precision Macro: 0.5021
|
| 26 |
+
- Precision Micro: 0.5758
|
| 27 |
+
- Precision Weighted: 0.5657
|
| 28 |
+
- Recall Macro: 0.5073
|
| 29 |
+
- Recall Micro: 0.5758
|
| 30 |
+
- Recall Weighted: 0.5758
|
| 31 |
+
- Accuracy: 0.5758
|
| 32 |
+
|
| 33 |
+
## Model description
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Intended uses & limitations
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training and evaluation data
|
| 42 |
+
|
| 43 |
+
More information needed
|
| 44 |
+
|
| 45 |
+
## Training procedure
|
| 46 |
+
|
| 47 |
+
### Training hyperparameters
|
| 48 |
+
|
| 49 |
+
The following hyperparameters were used during training:
|
| 50 |
+
- learning_rate: 0.0001
|
| 51 |
+
- train_batch_size: 32
|
| 52 |
+
- eval_batch_size: 32
|
| 53 |
+
- seed: 42
|
| 54 |
+
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 55 |
+
- lr_scheduler_type: linear
|
| 56 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 57 |
+
- num_epochs: 30
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | F1 Weighted | Precision Macro | Precision Micro | Precision Weighted | Recall Macro | Recall Micro | Recall Weighted | Accuracy |
|
| 62 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------:|:---------------:|:---------------:|:------------------:|:------------:|:------------:|:---------------:|:--------:|
|
| 63 |
+
| 1.9373 | 1.0 | 15 | 1.8818 | 0.0464 | 0.1894 | 0.0615 | 0.0277 | 0.1894 | 0.0367 | 0.1429 | 0.1894 | 0.1894 | 0.1894 |
|
| 64 |
+
| 1.869 | 2.0 | 30 | 1.8642 | 0.1100 | 0.2652 | 0.1418 | 0.075 | 0.2652 | 0.0968 | 0.2063 | 0.2652 | 0.2652 | 0.2652 |
|
| 65 |
+
| 1.9218 | 3.0 | 45 | 1.8754 | 0.1163 | 0.2576 | 0.1460 | 0.1316 | 0.2576 | 0.1566 | 0.1905 | 0.2576 | 0.2576 | 0.2576 |
|
| 66 |
+
| 1.6733 | 4.0 | 60 | 1.6881 | 0.2445 | 0.3864 | 0.3053 | 0.2427 | 0.3864 | 0.2917 | 0.2992 | 0.3864 | 0.3864 | 0.3864 |
|
| 67 |
+
| 1.54 | 5.0 | 75 | 1.5528 | 0.3252 | 0.4242 | 0.3856 | 0.3429 | 0.4242 | 0.4101 | 0.3570 | 0.4242 | 0.4242 | 0.4242 |
|
| 68 |
+
| 1.4418 | 6.0 | 90 | 1.5737 | 0.2858 | 0.3864 | 0.3213 | 0.2846 | 0.3864 | 0.3243 | 0.3398 | 0.3864 | 0.3864 | 0.3864 |
|
| 69 |
+
| 0.8592 | 7.0 | 105 | 1.5408 | 0.3444 | 0.4394 | 0.3965 | 0.3208 | 0.4394 | 0.3674 | 0.3791 | 0.4394 | 0.4394 | 0.4394 |
|
| 70 |
+
| 1.1427 | 8.0 | 120 | 1.2804 | 0.4638 | 0.5606 | 0.5317 | 0.4698 | 0.5606 | 0.5280 | 0.4831 | 0.5606 | 0.5606 | 0.5606 |
|
| 71 |
+
| 0.7849 | 9.0 | 135 | 1.2880 | 0.4649 | 0.5530 | 0.5291 | 0.4804 | 0.5530 | 0.5401 | 0.4823 | 0.5530 | 0.5530 | 0.5530 |
|
| 72 |
+
| 0.6846 | 10.0 | 150 | 1.3130 | 0.4298 | 0.5152 | 0.4811 | 0.4404 | 0.5152 | 0.5005 | 0.4671 | 0.5152 | 0.5152 | 0.5152 |
|
| 73 |
+
| 0.4006 | 11.0 | 165 | 1.2958 | 0.4931 | 0.5833 | 0.5598 | 0.4983 | 0.5833 | 0.5756 | 0.5229 | 0.5833 | 0.5833 | 0.5833 |
|
| 74 |
+
| 0.4329 | 12.0 | 180 | 1.2990 | 0.5062 | 0.5530 | 0.5562 | 0.5315 | 0.5530 | 0.5874 | 0.5133 | 0.5530 | 0.5530 | 0.5530 |
|
| 75 |
+
| 0.482 | 13.0 | 195 | 1.3831 | 0.4842 | 0.5152 | 0.5233 | 0.5517 | 0.5152 | 0.5803 | 0.4839 | 0.5152 | 0.5152 | 0.5152 |
|
| 76 |
+
| 0.6409 | 14.0 | 210 | 1.4066 | 0.5081 | 0.5985 | 0.5765 | 0.5194 | 0.5985 | 0.5820 | 0.5232 | 0.5985 | 0.5985 | 0.5985 |
|
| 77 |
+
| 0.3206 | 15.0 | 225 | 1.3690 | 0.5155 | 0.5606 | 0.5520 | 0.6158 | 0.5606 | 0.5890 | 0.5170 | 0.5606 | 0.5606 | 0.5606 |
|
| 78 |
+
| 0.1773 | 16.0 | 240 | 1.2568 | 0.5920 | 0.6515 | 0.6408 | 0.6894 | 0.6515 | 0.6623 | 0.5843 | 0.6515 | 0.6515 | 0.6515 |
|
| 79 |
+
| 0.3259 | 17.0 | 255 | 1.3406 | 0.5467 | 0.6061 | 0.5961 | 0.5615 | 0.6061 | 0.6033 | 0.5467 | 0.6061 | 0.6061 | 0.6061 |
|
| 80 |
+
| 0.1123 | 18.0 | 270 | 1.3767 | 0.5868 | 0.6364 | 0.6306 | 0.6258 | 0.6364 | 0.6413 | 0.5785 | 0.6364 | 0.6364 | 0.6364 |
|
| 81 |
+
| 0.1129 | 19.0 | 285 | 1.4680 | 0.5879 | 0.6439 | 0.6306 | 0.6809 | 0.6439 | 0.6933 | 0.5806 | 0.6439 | 0.6439 | 0.6439 |
|
| 82 |
+
| 0.0651 | 20.0 | 300 | 1.4981 | 0.6655 | 0.6894 | 0.6876 | 0.7115 | 0.6894 | 0.7224 | 0.6511 | 0.6894 | 0.6894 | 0.6894 |
|
| 83 |
+
| 0.0685 | 21.0 | 315 | 1.4621 | 0.6091 | 0.6515 | 0.6494 | 0.6303 | 0.6515 | 0.6641 | 0.6040 | 0.6515 | 0.6515 | 0.6515 |
|
| 84 |
+
| 0.1469 | 22.0 | 330 | 1.5347 | 0.5330 | 0.6212 | 0.6040 | 0.5477 | 0.6212 | 0.6149 | 0.5440 | 0.6212 | 0.6212 | 0.6212 |
|
| 85 |
+
| 0.0289 | 23.0 | 345 | 1.5417 | 0.5466 | 0.6288 | 0.6180 | 0.5409 | 0.6288 | 0.6108 | 0.5549 | 0.6288 | 0.6288 | 0.6288 |
|
| 86 |
+
| 0.01 | 24.0 | 360 | 1.5670 | 0.5475 | 0.6364 | 0.6187 | 0.5435 | 0.6364 | 0.6104 | 0.5594 | 0.6364 | 0.6364 | 0.6364 |
|
| 87 |
+
| 0.035 | 25.0 | 375 | 1.6037 | 0.5529 | 0.6364 | 0.6209 | 0.5470 | 0.6364 | 0.6156 | 0.5679 | 0.6364 | 0.6364 | 0.6364 |
|
| 88 |
+
| 0.0109 | 26.0 | 390 | 1.6752 | 0.5897 | 0.6212 | 0.6203 | 0.6145 | 0.6212 | 0.6527 | 0.6000 | 0.6212 | 0.6212 | 0.6212 |
|
| 89 |
+
| 0.038 | 27.0 | 405 | 1.6724 | 0.5344 | 0.6136 | 0.6008 | 0.5332 | 0.6136 | 0.6005 | 0.5468 | 0.6136 | 0.6136 | 0.6136 |
|
| 90 |
+
| 0.0116 | 28.0 | 420 | 1.6252 | 0.5384 | 0.6212 | 0.6090 | 0.5337 | 0.6212 | 0.6033 | 0.5491 | 0.6212 | 0.6212 | 0.6212 |
|
| 91 |
+
| 0.006 | 29.0 | 435 | 1.5980 | 0.5572 | 0.6364 | 0.6294 | 0.5529 | 0.6364 | 0.6246 | 0.5634 | 0.6364 | 0.6364 | 0.6364 |
|
| 92 |
+
| 0.0046 | 30.0 | 450 | 1.5939 | 0.5605 | 0.6439 | 0.6342 | 0.5546 | 0.6439 | 0.6269 | 0.5687 | 0.6439 | 0.6439 | 0.6439 |
|
| 93 |
+
|
| 94 |
+
|
| 95 |
+
### Framework versions
|
| 96 |
+
|
| 97 |
+
- Transformers 4.48.2
|
| 98 |
+
- Pytorch 2.6.0+cu124
|
| 99 |
+
- Datasets 3.2.0
|
| 100 |
+
- Tokenizers 0.21.0
|
all_results.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.5757575757575758,
|
| 4 |
+
"eval_f1_macro": 0.5018613142408387,
|
| 5 |
+
"eval_f1_micro": 0.5757575757575758,
|
| 6 |
+
"eval_f1_weighted": 0.5678870521449232,
|
| 7 |
+
"eval_loss": 1.6241134405136108,
|
| 8 |
+
"eval_precision_macro": 0.5021312021312021,
|
| 9 |
+
"eval_precision_micro": 0.5757575757575758,
|
| 10 |
+
"eval_precision_weighted": 0.5657130748039839,
|
| 11 |
+
"eval_recall_macro": 0.507312925170068,
|
| 12 |
+
"eval_recall_micro": 0.5757575757575758,
|
| 13 |
+
"eval_recall_weighted": 0.5757575757575758,
|
| 14 |
+
"eval_runtime": 1.861,
|
| 15 |
+
"eval_samples_per_second": 35.465,
|
| 16 |
+
"eval_steps_per_second": 1.612,
|
| 17 |
+
"total_flos": 1.0740871074163507e+18,
|
| 18 |
+
"train_loss": 0.6009381743893027,
|
| 19 |
+
"train_runtime": 318.0836,
|
| 20 |
+
"train_samples_per_second": 43.573,
|
| 21 |
+
"train_steps_per_second": 1.415
|
| 22 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/vit-base-patch16-224",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "-",
|
| 13 |
+
"1": "0",
|
| 14 |
+
"2": "1",
|
| 15 |
+
"3": "2",
|
| 16 |
+
"4": "3",
|
| 17 |
+
"5": "4",
|
| 18 |
+
"6": "5"
|
| 19 |
+
},
|
| 20 |
+
"image_size": 224,
|
| 21 |
+
"initializer_range": 0.02,
|
| 22 |
+
"intermediate_size": 3072,
|
| 23 |
+
"label2id": {
|
| 24 |
+
"-": "0",
|
| 25 |
+
"0": "1",
|
| 26 |
+
"1": "2",
|
| 27 |
+
"2": "3",
|
| 28 |
+
"3": "4",
|
| 29 |
+
"4": "5",
|
| 30 |
+
"5": "6"
|
| 31 |
+
},
|
| 32 |
+
"layer_norm_eps": 1e-12,
|
| 33 |
+
"model_type": "vit",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_channels": 3,
|
| 36 |
+
"num_hidden_layers": 12,
|
| 37 |
+
"patch_size": 16,
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"qkv_bias": true,
|
| 40 |
+
"torch_dtype": "float32",
|
| 41 |
+
"transformers_version": "4.48.2"
|
| 42 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.5757575757575758,
|
| 4 |
+
"eval_f1_macro": 0.5018613142408387,
|
| 5 |
+
"eval_f1_micro": 0.5757575757575758,
|
| 6 |
+
"eval_f1_weighted": 0.5678870521449232,
|
| 7 |
+
"eval_loss": 1.6241134405136108,
|
| 8 |
+
"eval_precision_macro": 0.5021312021312021,
|
| 9 |
+
"eval_precision_micro": 0.5757575757575758,
|
| 10 |
+
"eval_precision_weighted": 0.5657130748039839,
|
| 11 |
+
"eval_recall_macro": 0.507312925170068,
|
| 12 |
+
"eval_recall_micro": 0.5757575757575758,
|
| 13 |
+
"eval_recall_weighted": 0.5757575757575758,
|
| 14 |
+
"eval_runtime": 1.861,
|
| 15 |
+
"eval_samples_per_second": 35.465,
|
| 16 |
+
"eval_steps_per_second": 1.612
|
| 17 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65861e669959f8c3f7f1bdbce403590929e54edd1ddeaa1660e460a3fca9e422
|
| 3 |
+
size 343239356
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": null,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "ViTImageProcessorFast",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"resample": 2,
|
| 18 |
+
"rescale_factor": 0.00392156862745098,
|
| 19 |
+
"size": {
|
| 20 |
+
"height": 224,
|
| 21 |
+
"width": 224
|
| 22 |
+
}
|
| 23 |
+
}
|
runs/Feb03_18-39-25_modal/events.out.tfevents.1738607969.modal.2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cd989b88e11140fc6612945f3f7d2d919ead3e8579dedebdc02d74bd664ecf7
|
| 3 |
+
size 77614
|
runs/Feb03_18-39-25_modal/events.out.tfevents.1738607969.modal.2.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60506e5bdcf9035c18a7a76f00ef4c884b93b73d0cd6160a4e0846b0bd8b84cd
|
| 3 |
+
size 77614
|
runs/Feb03_18-39-25_modal/events.out.tfevents.1738608289.modal.2.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8a81371ec31b0a5fd49b41237e342cd559386d392f1f383ae7e97a52a39b236
|
| 3 |
+
size 921
|
runs/Feb03_18-39-25_modal/events.out.tfevents.1738608289.modal.2.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b59892af0c2cb0cc3ad9df5062ebc403f3a72c05b2609845d133345e4574707
|
| 3 |
+
size 921
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 30.0,
|
| 3 |
+
"total_flos": 1.0740871074163507e+18,
|
| 4 |
+
"train_loss": 0.6009381743893027,
|
| 5 |
+
"train_runtime": 318.0836,
|
| 6 |
+
"train_samples_per_second": 43.573,
|
| 7 |
+
"train_steps_per_second": 1.415
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.2568100690841675,
|
| 3 |
+
"best_model_checkpoint": "square_run_32_batch/checkpoint-240",
|
| 4 |
+
"epoch": 30.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 450,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13333333333333333,
|
| 13 |
+
"grad_norm": 6.848705291748047,
|
| 14 |
+
"learning_rate": 4.444444444444445e-06,
|
| 15 |
+
"loss": 2.0193,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.26666666666666666,
|
| 20 |
+
"grad_norm": 5.4228925704956055,
|
| 21 |
+
"learning_rate": 8.88888888888889e-06,
|
| 22 |
+
"loss": 2.1013,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.4,
|
| 27 |
+
"grad_norm": 4.7422590255737305,
|
| 28 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 29 |
+
"loss": 1.9569,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5333333333333333,
|
| 34 |
+
"grad_norm": 5.0756025314331055,
|
| 35 |
+
"learning_rate": 1.777777777777778e-05,
|
| 36 |
+
"loss": 1.9677,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.6666666666666666,
|
| 41 |
+
"grad_norm": 7.1845269203186035,
|
| 42 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 43 |
+
"loss": 1.884,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8,
|
| 48 |
+
"grad_norm": 4.051375865936279,
|
| 49 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 50 |
+
"loss": 1.9017,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.9333333333333333,
|
| 55 |
+
"grad_norm": 5.293440341949463,
|
| 56 |
+
"learning_rate": 3.111111111111111e-05,
|
| 57 |
+
"loss": 1.9373,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"eval_accuracy": 0.1893939393939394,
|
| 63 |
+
"eval_f1_macro": 0.04638218923933209,
|
| 64 |
+
"eval_f1_micro": 0.1893939393939394,
|
| 65 |
+
"eval_f1_weighted": 0.06149153876426603,
|
| 66 |
+
"eval_loss": 1.8818118572235107,
|
| 67 |
+
"eval_precision_macro": 0.027685492801771874,
|
| 68 |
+
"eval_precision_micro": 0.1893939393939394,
|
| 69 |
+
"eval_precision_weighted": 0.03670425182053089,
|
| 70 |
+
"eval_recall_macro": 0.14285714285714285,
|
| 71 |
+
"eval_recall_micro": 0.1893939393939394,
|
| 72 |
+
"eval_recall_weighted": 0.1893939393939394,
|
| 73 |
+
"eval_runtime": 2.2684,
|
| 74 |
+
"eval_samples_per_second": 58.192,
|
| 75 |
+
"eval_steps_per_second": 2.204,
|
| 76 |
+
"step": 15
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.0666666666666667,
|
| 80 |
+
"grad_norm": 3.4230170249938965,
|
| 81 |
+
"learning_rate": 3.555555555555556e-05,
|
| 82 |
+
"loss": 1.9179,
|
| 83 |
+
"step": 16
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 1.2,
|
| 87 |
+
"grad_norm": 3.4030396938323975,
|
| 88 |
+
"learning_rate": 4e-05,
|
| 89 |
+
"loss": 1.8139,
|
| 90 |
+
"step": 18
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.3333333333333333,
|
| 94 |
+
"grad_norm": 4.195278167724609,
|
| 95 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 96 |
+
"loss": 1.8941,
|
| 97 |
+
"step": 20
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.4666666666666668,
|
| 101 |
+
"grad_norm": 3.2356927394866943,
|
| 102 |
+
"learning_rate": 4.888888888888889e-05,
|
| 103 |
+
"loss": 1.8915,
|
| 104 |
+
"step": 22
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.6,
|
| 108 |
+
"grad_norm": 3.322704315185547,
|
| 109 |
+
"learning_rate": 5.333333333333333e-05,
|
| 110 |
+
"loss": 1.917,
|
| 111 |
+
"step": 24
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.7333333333333334,
|
| 115 |
+
"grad_norm": 3.293910026550293,
|
| 116 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 117 |
+
"loss": 1.8943,
|
| 118 |
+
"step": 26
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 1.8666666666666667,
|
| 122 |
+
"grad_norm": 4.803905487060547,
|
| 123 |
+
"learning_rate": 6.222222222222222e-05,
|
| 124 |
+
"loss": 1.8841,
|
| 125 |
+
"step": 28
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 2.0,
|
| 129 |
+
"grad_norm": 4.006722927093506,
|
| 130 |
+
"learning_rate": 6.666666666666667e-05,
|
| 131 |
+
"loss": 1.869,
|
| 132 |
+
"step": 30
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 2.0,
|
| 136 |
+
"eval_accuracy": 0.26515151515151514,
|
| 137 |
+
"eval_f1_macro": 0.10998877665544333,
|
| 138 |
+
"eval_f1_micro": 0.26515151515151514,
|
| 139 |
+
"eval_f1_weighted": 0.14177124783185388,
|
| 140 |
+
"eval_loss": 1.864223599433899,
|
| 141 |
+
"eval_precision_macro": 0.075,
|
| 142 |
+
"eval_precision_micro": 0.26515151515151514,
|
| 143 |
+
"eval_precision_weighted": 0.09678030303030305,
|
| 144 |
+
"eval_recall_macro": 0.20634920634920634,
|
| 145 |
+
"eval_recall_micro": 0.26515151515151514,
|
| 146 |
+
"eval_recall_weighted": 0.26515151515151514,
|
| 147 |
+
"eval_runtime": 1.8754,
|
| 148 |
+
"eval_samples_per_second": 70.384,
|
| 149 |
+
"eval_steps_per_second": 2.666,
|
| 150 |
+
"step": 30
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.1333333333333333,
|
| 154 |
+
"grad_norm": 2.15875506401062,
|
| 155 |
+
"learning_rate": 7.111111111111112e-05,
|
| 156 |
+
"loss": 1.8686,
|
| 157 |
+
"step": 32
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.2666666666666666,
|
| 161 |
+
"grad_norm": 2.8864150047302246,
|
| 162 |
+
"learning_rate": 7.555555555555556e-05,
|
| 163 |
+
"loss": 1.8652,
|
| 164 |
+
"step": 34
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.4,
|
| 168 |
+
"grad_norm": 3.819974899291992,
|
| 169 |
+
"learning_rate": 8e-05,
|
| 170 |
+
"loss": 1.818,
|
| 171 |
+
"step": 36
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.533333333333333,
|
| 175 |
+
"grad_norm": 7.35491418838501,
|
| 176 |
+
"learning_rate": 8.444444444444444e-05,
|
| 177 |
+
"loss": 1.9347,
|
| 178 |
+
"step": 38
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.6666666666666665,
|
| 182 |
+
"grad_norm": 5.84605598449707,
|
| 183 |
+
"learning_rate": 8.888888888888889e-05,
|
| 184 |
+
"loss": 1.8508,
|
| 185 |
+
"step": 40
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.8,
|
| 189 |
+
"grad_norm": 2.4050137996673584,
|
| 190 |
+
"learning_rate": 9.333333333333334e-05,
|
| 191 |
+
"loss": 1.8884,
|
| 192 |
+
"step": 42
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.9333333333333336,
|
| 196 |
+
"grad_norm": 5.182938575744629,
|
| 197 |
+
"learning_rate": 9.777777777777778e-05,
|
| 198 |
+
"loss": 1.9218,
|
| 199 |
+
"step": 44
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.0,
|
| 203 |
+
"eval_accuracy": 0.25757575757575757,
|
| 204 |
+
"eval_f1_macro": 0.11628985865833667,
|
| 205 |
+
"eval_f1_micro": 0.25757575757575757,
|
| 206 |
+
"eval_f1_weighted": 0.1459780747505363,
|
| 207 |
+
"eval_loss": 1.8754385709762573,
|
| 208 |
+
"eval_precision_macro": 0.131615925058548,
|
| 209 |
+
"eval_precision_micro": 0.25757575757575757,
|
| 210 |
+
"eval_precision_weighted": 0.15663189269746647,
|
| 211 |
+
"eval_recall_macro": 0.19047619047619047,
|
| 212 |
+
"eval_recall_micro": 0.25757575757575757,
|
| 213 |
+
"eval_recall_weighted": 0.25757575757575757,
|
| 214 |
+
"eval_runtime": 1.9051,
|
| 215 |
+
"eval_samples_per_second": 69.286,
|
| 216 |
+
"eval_steps_per_second": 2.624,
|
| 217 |
+
"step": 45
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 3.066666666666667,
|
| 221 |
+
"grad_norm": 5.7963128089904785,
|
| 222 |
+
"learning_rate": 9.97530864197531e-05,
|
| 223 |
+
"loss": 1.9754,
|
| 224 |
+
"step": 46
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.2,
|
| 228 |
+
"grad_norm": 5.1605048179626465,
|
| 229 |
+
"learning_rate": 9.925925925925926e-05,
|
| 230 |
+
"loss": 1.8577,
|
| 231 |
+
"step": 48
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 3.3333333333333335,
|
| 235 |
+
"grad_norm": 3.756355047225952,
|
| 236 |
+
"learning_rate": 9.876543209876543e-05,
|
| 237 |
+
"loss": 1.8707,
|
| 238 |
+
"step": 50
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 3.466666666666667,
|
| 242 |
+
"grad_norm": 2.5353710651397705,
|
| 243 |
+
"learning_rate": 9.827160493827162e-05,
|
| 244 |
+
"loss": 1.7918,
|
| 245 |
+
"step": 52
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 3.6,
|
| 249 |
+
"grad_norm": 4.181753635406494,
|
| 250 |
+
"learning_rate": 9.777777777777778e-05,
|
| 251 |
+
"loss": 1.8251,
|
| 252 |
+
"step": 54
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3.7333333333333334,
|
| 256 |
+
"grad_norm": 2.4634644985198975,
|
| 257 |
+
"learning_rate": 9.728395061728396e-05,
|
| 258 |
+
"loss": 1.7713,
|
| 259 |
+
"step": 56
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 3.8666666666666667,
|
| 263 |
+
"grad_norm": 8.700553894042969,
|
| 264 |
+
"learning_rate": 9.679012345679013e-05,
|
| 265 |
+
"loss": 1.8962,
|
| 266 |
+
"step": 58
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.0,
|
| 270 |
+
"grad_norm": 5.921916484832764,
|
| 271 |
+
"learning_rate": 9.62962962962963e-05,
|
| 272 |
+
"loss": 1.6733,
|
| 273 |
+
"step": 60
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 4.0,
|
| 277 |
+
"eval_accuracy": 0.38636363636363635,
|
| 278 |
+
"eval_f1_macro": 0.2445293836598184,
|
| 279 |
+
"eval_f1_micro": 0.38636363636363635,
|
| 280 |
+
"eval_f1_weighted": 0.3052538765582244,
|
| 281 |
+
"eval_loss": 1.6881486177444458,
|
| 282 |
+
"eval_precision_macro": 0.24274221103966703,
|
| 283 |
+
"eval_precision_micro": 0.38636363636363635,
|
| 284 |
+
"eval_precision_weighted": 0.2917426054412356,
|
| 285 |
+
"eval_recall_macro": 0.2992441421012849,
|
| 286 |
+
"eval_recall_micro": 0.38636363636363635,
|
| 287 |
+
"eval_recall_weighted": 0.38636363636363635,
|
| 288 |
+
"eval_runtime": 1.8719,
|
| 289 |
+
"eval_samples_per_second": 70.516,
|
| 290 |
+
"eval_steps_per_second": 2.671,
|
| 291 |
+
"step": 60
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 4.133333333333334,
|
| 295 |
+
"grad_norm": 3.3924758434295654,
|
| 296 |
+
"learning_rate": 9.580246913580247e-05,
|
| 297 |
+
"loss": 1.5941,
|
| 298 |
+
"step": 62
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 4.266666666666667,
|
| 302 |
+
"grad_norm": 6.785348415374756,
|
| 303 |
+
"learning_rate": 9.530864197530865e-05,
|
| 304 |
+
"loss": 1.582,
|
| 305 |
+
"step": 64
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.4,
|
| 309 |
+
"grad_norm": 4.813143730163574,
|
| 310 |
+
"learning_rate": 9.481481481481483e-05,
|
| 311 |
+
"loss": 1.649,
|
| 312 |
+
"step": 66
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 4.533333333333333,
|
| 316 |
+
"grad_norm": 5.351255893707275,
|
| 317 |
+
"learning_rate": 9.432098765432099e-05,
|
| 318 |
+
"loss": 1.6271,
|
| 319 |
+
"step": 68
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 4.666666666666667,
|
| 323 |
+
"grad_norm": 11.194862365722656,
|
| 324 |
+
"learning_rate": 9.382716049382717e-05,
|
| 325 |
+
"loss": 1.7395,
|
| 326 |
+
"step": 70
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.8,
|
| 330 |
+
"grad_norm": 6.263866424560547,
|
| 331 |
+
"learning_rate": 9.333333333333334e-05,
|
| 332 |
+
"loss": 1.4422,
|
| 333 |
+
"step": 72
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 4.933333333333334,
|
| 337 |
+
"grad_norm": 8.602386474609375,
|
| 338 |
+
"learning_rate": 9.28395061728395e-05,
|
| 339 |
+
"loss": 1.54,
|
| 340 |
+
"step": 74
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 5.0,
|
| 344 |
+
"eval_accuracy": 0.42424242424242425,
|
| 345 |
+
"eval_f1_macro": 0.32515713851372885,
|
| 346 |
+
"eval_f1_micro": 0.42424242424242425,
|
| 347 |
+
"eval_f1_weighted": 0.38558697740383735,
|
| 348 |
+
"eval_loss": 1.5528110265731812,
|
| 349 |
+
"eval_precision_macro": 0.34291374508765815,
|
| 350 |
+
"eval_precision_micro": 0.42424242424242425,
|
| 351 |
+
"eval_precision_weighted": 0.4100833883442579,
|
| 352 |
+
"eval_recall_macro": 0.35698412698412696,
|
| 353 |
+
"eval_recall_micro": 0.42424242424242425,
|
| 354 |
+
"eval_recall_weighted": 0.42424242424242425,
|
| 355 |
+
"eval_runtime": 1.9443,
|
| 356 |
+
"eval_samples_per_second": 67.891,
|
| 357 |
+
"eval_steps_per_second": 2.572,
|
| 358 |
+
"step": 75
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 5.066666666666666,
|
| 362 |
+
"grad_norm": 7.738183498382568,
|
| 363 |
+
"learning_rate": 9.234567901234568e-05,
|
| 364 |
+
"loss": 1.6152,
|
| 365 |
+
"step": 76
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 5.2,
|
| 369 |
+
"grad_norm": 7.564102649688721,
|
| 370 |
+
"learning_rate": 9.185185185185186e-05,
|
| 371 |
+
"loss": 1.4993,
|
| 372 |
+
"step": 78
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 5.333333333333333,
|
| 376 |
+
"grad_norm": 8.335043907165527,
|
| 377 |
+
"learning_rate": 9.135802469135802e-05,
|
| 378 |
+
"loss": 1.494,
|
| 379 |
+
"step": 80
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 5.466666666666667,
|
| 383 |
+
"grad_norm": 6.382967948913574,
|
| 384 |
+
"learning_rate": 9.08641975308642e-05,
|
| 385 |
+
"loss": 1.4944,
|
| 386 |
+
"step": 82
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.6,
|
| 390 |
+
"grad_norm": 7.259094715118408,
|
| 391 |
+
"learning_rate": 9.037037037037038e-05,
|
| 392 |
+
"loss": 1.3191,
|
| 393 |
+
"step": 84
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 5.733333333333333,
|
| 397 |
+
"grad_norm": 4.972009658813477,
|
| 398 |
+
"learning_rate": 8.987654320987655e-05,
|
| 399 |
+
"loss": 1.3894,
|
| 400 |
+
"step": 86
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 5.866666666666667,
|
| 404 |
+
"grad_norm": 9.250694274902344,
|
| 405 |
+
"learning_rate": 8.938271604938272e-05,
|
| 406 |
+
"loss": 1.3979,
|
| 407 |
+
"step": 88
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 6.0,
|
| 411 |
+
"grad_norm": 7.207069396972656,
|
| 412 |
+
"learning_rate": 8.888888888888889e-05,
|
| 413 |
+
"loss": 1.4418,
|
| 414 |
+
"step": 90
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 6.0,
|
| 418 |
+
"eval_accuracy": 0.38636363636363635,
|
| 419 |
+
"eval_f1_macro": 0.285838283865586,
|
| 420 |
+
"eval_f1_micro": 0.38636363636363635,
|
| 421 |
+
"eval_f1_weighted": 0.3212562379097532,
|
| 422 |
+
"eval_loss": 1.5736558437347412,
|
| 423 |
+
"eval_precision_macro": 0.284608858206039,
|
| 424 |
+
"eval_precision_micro": 0.38636363636363635,
|
| 425 |
+
"eval_precision_weighted": 0.3242631096693543,
|
| 426 |
+
"eval_recall_macro": 0.3398034769463341,
|
| 427 |
+
"eval_recall_micro": 0.38636363636363635,
|
| 428 |
+
"eval_recall_weighted": 0.38636363636363635,
|
| 429 |
+
"eval_runtime": 1.8593,
|
| 430 |
+
"eval_samples_per_second": 70.995,
|
| 431 |
+
"eval_steps_per_second": 2.689,
|
| 432 |
+
"step": 90
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 6.133333333333334,
|
| 436 |
+
"grad_norm": 4.753687381744385,
|
| 437 |
+
"learning_rate": 8.839506172839507e-05,
|
| 438 |
+
"loss": 1.3218,
|
| 439 |
+
"step": 92
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 6.266666666666667,
|
| 443 |
+
"grad_norm": 5.942229747772217,
|
| 444 |
+
"learning_rate": 8.790123456790123e-05,
|
| 445 |
+
"loss": 1.3995,
|
| 446 |
+
"step": 94
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 6.4,
|
| 450 |
+
"grad_norm": 4.026015281677246,
|
| 451 |
+
"learning_rate": 8.740740740740741e-05,
|
| 452 |
+
"loss": 1.3155,
|
| 453 |
+
"step": 96
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 6.533333333333333,
|
| 457 |
+
"grad_norm": 4.893887042999268,
|
| 458 |
+
"learning_rate": 8.691358024691359e-05,
|
| 459 |
+
"loss": 1.2009,
|
| 460 |
+
"step": 98
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 6.666666666666667,
|
| 464 |
+
"grad_norm": 3.904926061630249,
|
| 465 |
+
"learning_rate": 8.641975308641975e-05,
|
| 466 |
+
"loss": 0.98,
|
| 467 |
+
"step": 100
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 6.8,
|
| 471 |
+
"grad_norm": 4.266864776611328,
|
| 472 |
+
"learning_rate": 8.592592592592593e-05,
|
| 473 |
+
"loss": 1.0803,
|
| 474 |
+
"step": 102
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 6.933333333333334,
|
| 478 |
+
"grad_norm": 5.24403190612793,
|
| 479 |
+
"learning_rate": 8.54320987654321e-05,
|
| 480 |
+
"loss": 0.8592,
|
| 481 |
+
"step": 104
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 7.0,
|
| 485 |
+
"eval_accuracy": 0.4393939393939394,
|
| 486 |
+
"eval_f1_macro": 0.3443599467808913,
|
| 487 |
+
"eval_f1_micro": 0.4393939393939394,
|
| 488 |
+
"eval_f1_weighted": 0.39645908811500513,
|
| 489 |
+
"eval_loss": 1.5408130884170532,
|
| 490 |
+
"eval_precision_macro": 0.32083233878346656,
|
| 491 |
+
"eval_precision_micro": 0.4393939393939394,
|
| 492 |
+
"eval_precision_weighted": 0.36735850041771095,
|
| 493 |
+
"eval_recall_macro": 0.37913832199546477,
|
| 494 |
+
"eval_recall_micro": 0.4393939393939394,
|
| 495 |
+
"eval_recall_weighted": 0.4393939393939394,
|
| 496 |
+
"eval_runtime": 1.9485,
|
| 497 |
+
"eval_samples_per_second": 67.743,
|
| 498 |
+
"eval_steps_per_second": 2.566,
|
| 499 |
+
"step": 105
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 7.066666666666666,
|
| 503 |
+
"grad_norm": 5.595825672149658,
|
| 504 |
+
"learning_rate": 8.493827160493828e-05,
|
| 505 |
+
"loss": 1.0203,
|
| 506 |
+
"step": 106
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 7.2,
|
| 510 |
+
"grad_norm": 5.34617805480957,
|
| 511 |
+
"learning_rate": 8.444444444444444e-05,
|
| 512 |
+
"loss": 1.0819,
|
| 513 |
+
"step": 108
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.333333333333333,
|
| 517 |
+
"grad_norm": 6.987905025482178,
|
| 518 |
+
"learning_rate": 8.395061728395062e-05,
|
| 519 |
+
"loss": 1.1165,
|
| 520 |
+
"step": 110
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.466666666666667,
|
| 524 |
+
"grad_norm": 6.039572715759277,
|
| 525 |
+
"learning_rate": 8.34567901234568e-05,
|
| 526 |
+
"loss": 1.0403,
|
| 527 |
+
"step": 112
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.6,
|
| 531 |
+
"grad_norm": 6.031858444213867,
|
| 532 |
+
"learning_rate": 8.296296296296296e-05,
|
| 533 |
+
"loss": 0.9709,
|
| 534 |
+
"step": 114
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.733333333333333,
|
| 538 |
+
"grad_norm": 6.656283855438232,
|
| 539 |
+
"learning_rate": 8.246913580246915e-05,
|
| 540 |
+
"loss": 0.8358,
|
| 541 |
+
"step": 116
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.866666666666667,
|
| 545 |
+
"grad_norm": 6.286685943603516,
|
| 546 |
+
"learning_rate": 8.197530864197531e-05,
|
| 547 |
+
"loss": 1.146,
|
| 548 |
+
"step": 118
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 8.0,
|
| 552 |
+
"grad_norm": 9.892986297607422,
|
| 553 |
+
"learning_rate": 8.148148148148148e-05,
|
| 554 |
+
"loss": 1.1427,
|
| 555 |
+
"step": 120
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 8.0,
|
| 559 |
+
"eval_accuracy": 0.5606060606060606,
|
| 560 |
+
"eval_f1_macro": 0.46377203827822905,
|
| 561 |
+
"eval_f1_micro": 0.5606060606060606,
|
| 562 |
+
"eval_f1_weighted": 0.5317054176401353,
|
| 563 |
+
"eval_loss": 1.2803829908370972,
|
| 564 |
+
"eval_precision_macro": 0.469819473380193,
|
| 565 |
+
"eval_precision_micro": 0.5606060606060606,
|
| 566 |
+
"eval_precision_weighted": 0.5280005916463256,
|
| 567 |
+
"eval_recall_macro": 0.4830687830687831,
|
| 568 |
+
"eval_recall_micro": 0.5606060606060606,
|
| 569 |
+
"eval_recall_weighted": 0.5606060606060606,
|
| 570 |
+
"eval_runtime": 1.9474,
|
| 571 |
+
"eval_samples_per_second": 67.784,
|
| 572 |
+
"eval_steps_per_second": 2.568,
|
| 573 |
+
"step": 120
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 8.133333333333333,
|
| 577 |
+
"grad_norm": 4.904130458831787,
|
| 578 |
+
"learning_rate": 8.098765432098767e-05,
|
| 579 |
+
"loss": 0.8933,
|
| 580 |
+
"step": 122
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 8.266666666666667,
|
| 584 |
+
"grad_norm": 4.419686794281006,
|
| 585 |
+
"learning_rate": 8.049382716049383e-05,
|
| 586 |
+
"loss": 0.9245,
|
| 587 |
+
"step": 124
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 8.4,
|
| 591 |
+
"grad_norm": 8.33668041229248,
|
| 592 |
+
"learning_rate": 8e-05,
|
| 593 |
+
"loss": 0.8385,
|
| 594 |
+
"step": 126
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 8.533333333333333,
|
| 598 |
+
"grad_norm": 8.35203742980957,
|
| 599 |
+
"learning_rate": 7.950617283950618e-05,
|
| 600 |
+
"loss": 0.9428,
|
| 601 |
+
"step": 128
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 8.666666666666666,
|
| 605 |
+
"grad_norm": 5.724539279937744,
|
| 606 |
+
"learning_rate": 7.901234567901235e-05,
|
| 607 |
+
"loss": 0.7591,
|
| 608 |
+
"step": 130
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 8.8,
|
| 612 |
+
"grad_norm": 8.662413597106934,
|
| 613 |
+
"learning_rate": 7.851851851851852e-05,
|
| 614 |
+
"loss": 0.995,
|
| 615 |
+
"step": 132
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 8.933333333333334,
|
| 619 |
+
"grad_norm": 5.197690010070801,
|
| 620 |
+
"learning_rate": 7.802469135802469e-05,
|
| 621 |
+
"loss": 0.7849,
|
| 622 |
+
"step": 134
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 9.0,
|
| 626 |
+
"eval_accuracy": 0.553030303030303,
|
| 627 |
+
"eval_f1_macro": 0.46486536691732006,
|
| 628 |
+
"eval_f1_micro": 0.553030303030303,
|
| 629 |
+
"eval_f1_weighted": 0.529141811901771,
|
| 630 |
+
"eval_loss": 1.2879999876022339,
|
| 631 |
+
"eval_precision_macro": 0.48036078903674717,
|
| 632 |
+
"eval_precision_micro": 0.553030303030303,
|
| 633 |
+
"eval_precision_weighted": 0.540143107077697,
|
| 634 |
+
"eval_recall_macro": 0.4822675736961451,
|
| 635 |
+
"eval_recall_micro": 0.553030303030303,
|
| 636 |
+
"eval_recall_weighted": 0.553030303030303,
|
| 637 |
+
"eval_runtime": 1.9912,
|
| 638 |
+
"eval_samples_per_second": 66.292,
|
| 639 |
+
"eval_steps_per_second": 2.511,
|
| 640 |
+
"step": 135
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 9.066666666666666,
|
| 644 |
+
"grad_norm": 7.03670597076416,
|
| 645 |
+
"learning_rate": 7.753086419753088e-05,
|
| 646 |
+
"loss": 0.8049,
|
| 647 |
+
"step": 136
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 9.2,
|
| 651 |
+
"grad_norm": 5.591729640960693,
|
| 652 |
+
"learning_rate": 7.703703703703704e-05,
|
| 653 |
+
"loss": 0.9341,
|
| 654 |
+
"step": 138
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 9.333333333333334,
|
| 658 |
+
"grad_norm": 6.677962303161621,
|
| 659 |
+
"learning_rate": 7.65432098765432e-05,
|
| 660 |
+
"loss": 0.7679,
|
| 661 |
+
"step": 140
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 9.466666666666667,
|
| 665 |
+
"grad_norm": 5.4789934158325195,
|
| 666 |
+
"learning_rate": 7.60493827160494e-05,
|
| 667 |
+
"loss": 0.7773,
|
| 668 |
+
"step": 142
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 9.6,
|
| 672 |
+
"grad_norm": 5.957266330718994,
|
| 673 |
+
"learning_rate": 7.555555555555556e-05,
|
| 674 |
+
"loss": 0.638,
|
| 675 |
+
"step": 144
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 9.733333333333333,
|
| 679 |
+
"grad_norm": 5.691118240356445,
|
| 680 |
+
"learning_rate": 7.506172839506173e-05,
|
| 681 |
+
"loss": 0.7762,
|
| 682 |
+
"step": 146
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 9.866666666666667,
|
| 686 |
+
"grad_norm": 6.8899827003479,
|
| 687 |
+
"learning_rate": 7.456790123456791e-05,
|
| 688 |
+
"loss": 0.9012,
|
| 689 |
+
"step": 148
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 10.0,
|
| 693 |
+
"grad_norm": 7.408969402313232,
|
| 694 |
+
"learning_rate": 7.407407407407407e-05,
|
| 695 |
+
"loss": 0.6846,
|
| 696 |
+
"step": 150
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 10.0,
|
| 700 |
+
"eval_accuracy": 0.5151515151515151,
|
| 701 |
+
"eval_f1_macro": 0.42983280392444223,
|
| 702 |
+
"eval_f1_micro": 0.5151515151515151,
|
| 703 |
+
"eval_f1_weighted": 0.48105498068393227,
|
| 704 |
+
"eval_loss": 1.3130199909210205,
|
| 705 |
+
"eval_precision_macro": 0.4404005812415951,
|
| 706 |
+
"eval_precision_micro": 0.5151515151515151,
|
| 707 |
+
"eval_precision_weighted": 0.5005354338015628,
|
| 708 |
+
"eval_recall_macro": 0.4670748299319728,
|
| 709 |
+
"eval_recall_micro": 0.5151515151515151,
|
| 710 |
+
"eval_recall_weighted": 0.5151515151515151,
|
| 711 |
+
"eval_runtime": 1.9855,
|
| 712 |
+
"eval_samples_per_second": 66.482,
|
| 713 |
+
"eval_steps_per_second": 2.518,
|
| 714 |
+
"step": 150
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 10.133333333333333,
|
| 718 |
+
"grad_norm": 5.070552825927734,
|
| 719 |
+
"learning_rate": 7.358024691358025e-05,
|
| 720 |
+
"loss": 0.6116,
|
| 721 |
+
"step": 152
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 10.266666666666667,
|
| 725 |
+
"grad_norm": 4.844223499298096,
|
| 726 |
+
"learning_rate": 7.308641975308643e-05,
|
| 727 |
+
"loss": 0.6517,
|
| 728 |
+
"step": 154
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 10.4,
|
| 732 |
+
"grad_norm": 3.965522289276123,
|
| 733 |
+
"learning_rate": 7.25925925925926e-05,
|
| 734 |
+
"loss": 0.5573,
|
| 735 |
+
"step": 156
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 10.533333333333333,
|
| 739 |
+
"grad_norm": 7.53262996673584,
|
| 740 |
+
"learning_rate": 7.209876543209877e-05,
|
| 741 |
+
"loss": 0.7258,
|
| 742 |
+
"step": 158
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 10.666666666666666,
|
| 746 |
+
"grad_norm": 6.725161552429199,
|
| 747 |
+
"learning_rate": 7.160493827160494e-05,
|
| 748 |
+
"loss": 0.8109,
|
| 749 |
+
"step": 160
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 10.8,
|
| 753 |
+
"grad_norm": 8.250865936279297,
|
| 754 |
+
"learning_rate": 7.111111111111112e-05,
|
| 755 |
+
"loss": 0.8596,
|
| 756 |
+
"step": 162
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 10.933333333333334,
|
| 760 |
+
"grad_norm": 4.163515567779541,
|
| 761 |
+
"learning_rate": 7.061728395061728e-05,
|
| 762 |
+
"loss": 0.4006,
|
| 763 |
+
"step": 164
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 11.0,
|
| 767 |
+
"eval_accuracy": 0.5833333333333334,
|
| 768 |
+
"eval_f1_macro": 0.49308835780529725,
|
| 769 |
+
"eval_f1_micro": 0.5833333333333334,
|
| 770 |
+
"eval_f1_weighted": 0.5597960736751899,
|
| 771 |
+
"eval_loss": 1.295769214630127,
|
| 772 |
+
"eval_precision_macro": 0.498317425896604,
|
| 773 |
+
"eval_precision_micro": 0.5833333333333334,
|
| 774 |
+
"eval_precision_weighted": 0.5756076561299337,
|
| 775 |
+
"eval_recall_macro": 0.5229024943310657,
|
| 776 |
+
"eval_recall_micro": 0.5833333333333334,
|
| 777 |
+
"eval_recall_weighted": 0.5833333333333334,
|
| 778 |
+
"eval_runtime": 1.9133,
|
| 779 |
+
"eval_samples_per_second": 68.991,
|
| 780 |
+
"eval_steps_per_second": 2.613,
|
| 781 |
+
"step": 165
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 11.066666666666666,
|
| 785 |
+
"grad_norm": 4.829576015472412,
|
| 786 |
+
"learning_rate": 7.012345679012346e-05,
|
| 787 |
+
"loss": 0.6355,
|
| 788 |
+
"step": 166
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 11.2,
|
| 792 |
+
"grad_norm": 5.353898525238037,
|
| 793 |
+
"learning_rate": 6.962962962962964e-05,
|
| 794 |
+
"loss": 0.4955,
|
| 795 |
+
"step": 168
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 11.333333333333334,
|
| 799 |
+
"grad_norm": 5.44912052154541,
|
| 800 |
+
"learning_rate": 6.91358024691358e-05,
|
| 801 |
+
"loss": 0.4833,
|
| 802 |
+
"step": 170
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 11.466666666666667,
|
| 806 |
+
"grad_norm": 5.900742530822754,
|
| 807 |
+
"learning_rate": 6.864197530864198e-05,
|
| 808 |
+
"loss": 0.5752,
|
| 809 |
+
"step": 172
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 11.6,
|
| 813 |
+
"grad_norm": 6.004303455352783,
|
| 814 |
+
"learning_rate": 6.814814814814815e-05,
|
| 815 |
+
"loss": 0.5738,
|
| 816 |
+
"step": 174
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 11.733333333333333,
|
| 820 |
+
"grad_norm": 3.937319040298462,
|
| 821 |
+
"learning_rate": 6.765432098765433e-05,
|
| 822 |
+
"loss": 0.4661,
|
| 823 |
+
"step": 176
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 11.866666666666667,
|
| 827 |
+
"grad_norm": 4.814683437347412,
|
| 828 |
+
"learning_rate": 6.716049382716049e-05,
|
| 829 |
+
"loss": 0.5694,
|
| 830 |
+
"step": 178
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 12.0,
|
| 834 |
+
"grad_norm": 6.7769880294799805,
|
| 835 |
+
"learning_rate": 6.666666666666667e-05,
|
| 836 |
+
"loss": 0.4329,
|
| 837 |
+
"step": 180
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 12.0,
|
| 841 |
+
"eval_accuracy": 0.553030303030303,
|
| 842 |
+
"eval_f1_macro": 0.506246746427407,
|
| 843 |
+
"eval_f1_micro": 0.553030303030303,
|
| 844 |
+
"eval_f1_weighted": 0.5561970515744254,
|
| 845 |
+
"eval_loss": 1.299007773399353,
|
| 846 |
+
"eval_precision_macro": 0.5314684490530354,
|
| 847 |
+
"eval_precision_micro": 0.553030303030303,
|
| 848 |
+
"eval_precision_weighted": 0.5874290165244113,
|
| 849 |
+
"eval_recall_macro": 0.5133106575963718,
|
| 850 |
+
"eval_recall_micro": 0.553030303030303,
|
| 851 |
+
"eval_recall_weighted": 0.553030303030303,
|
| 852 |
+
"eval_runtime": 2.0372,
|
| 853 |
+
"eval_samples_per_second": 64.793,
|
| 854 |
+
"eval_steps_per_second": 2.454,
|
| 855 |
+
"step": 180
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 12.133333333333333,
|
| 859 |
+
"grad_norm": 5.787886619567871,
|
| 860 |
+
"learning_rate": 6.617283950617285e-05,
|
| 861 |
+
"loss": 0.5719,
|
| 862 |
+
"step": 182
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 12.266666666666667,
|
| 866 |
+
"grad_norm": 2.843268632888794,
|
| 867 |
+
"learning_rate": 6.567901234567901e-05,
|
| 868 |
+
"loss": 0.4646,
|
| 869 |
+
"step": 184
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 12.4,
|
| 873 |
+
"grad_norm": 4.530274391174316,
|
| 874 |
+
"learning_rate": 6.51851851851852e-05,
|
| 875 |
+
"loss": 0.3544,
|
| 876 |
+
"step": 186
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 12.533333333333333,
|
| 880 |
+
"grad_norm": 5.348933696746826,
|
| 881 |
+
"learning_rate": 6.469135802469136e-05,
|
| 882 |
+
"loss": 0.3957,
|
| 883 |
+
"step": 188
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 12.666666666666666,
|
| 887 |
+
"grad_norm": 7.746328830718994,
|
| 888 |
+
"learning_rate": 6.419753086419753e-05,
|
| 889 |
+
"loss": 0.4989,
|
| 890 |
+
"step": 190
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 12.8,
|
| 894 |
+
"grad_norm": 6.134746074676514,
|
| 895 |
+
"learning_rate": 6.37037037037037e-05,
|
| 896 |
+
"loss": 0.7035,
|
| 897 |
+
"step": 192
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 12.933333333333334,
|
| 901 |
+
"grad_norm": 5.567310810089111,
|
| 902 |
+
"learning_rate": 6.320987654320988e-05,
|
| 903 |
+
"loss": 0.482,
|
| 904 |
+
"step": 194
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 13.0,
|
| 908 |
+
"eval_accuracy": 0.5151515151515151,
|
| 909 |
+
"eval_f1_macro": 0.4842067834885892,
|
| 910 |
+
"eval_f1_micro": 0.5151515151515151,
|
| 911 |
+
"eval_f1_weighted": 0.5233183119383529,
|
| 912 |
+
"eval_loss": 1.3830989599227905,
|
| 913 |
+
"eval_precision_macro": 0.5517290249433106,
|
| 914 |
+
"eval_precision_micro": 0.5151515151515151,
|
| 915 |
+
"eval_precision_weighted": 0.5803270803270804,
|
| 916 |
+
"eval_recall_macro": 0.48390778533635675,
|
| 917 |
+
"eval_recall_micro": 0.5151515151515151,
|
| 918 |
+
"eval_recall_weighted": 0.5151515151515151,
|
| 919 |
+
"eval_runtime": 2.882,
|
| 920 |
+
"eval_samples_per_second": 45.801,
|
| 921 |
+
"eval_steps_per_second": 1.735,
|
| 922 |
+
"step": 195
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 13.066666666666666,
|
| 926 |
+
"grad_norm": 6.7704386711120605,
|
| 927 |
+
"learning_rate": 6.271604938271606e-05,
|
| 928 |
+
"loss": 0.5136,
|
| 929 |
+
"step": 196
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 13.2,
|
| 933 |
+
"grad_norm": 5.41668701171875,
|
| 934 |
+
"learning_rate": 6.222222222222222e-05,
|
| 935 |
+
"loss": 0.4843,
|
| 936 |
+
"step": 198
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 13.333333333333334,
|
| 940 |
+
"grad_norm": 4.7562150955200195,
|
| 941 |
+
"learning_rate": 6.17283950617284e-05,
|
| 942 |
+
"loss": 0.3338,
|
| 943 |
+
"step": 200
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 13.466666666666667,
|
| 947 |
+
"grad_norm": 4.077147960662842,
|
| 948 |
+
"learning_rate": 6.123456790123457e-05,
|
| 949 |
+
"loss": 0.2694,
|
| 950 |
+
"step": 202
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 13.6,
|
| 954 |
+
"grad_norm": 4.678223609924316,
|
| 955 |
+
"learning_rate": 6.074074074074074e-05,
|
| 956 |
+
"loss": 0.2965,
|
| 957 |
+
"step": 204
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 13.733333333333333,
|
| 961 |
+
"grad_norm": 6.246657371520996,
|
| 962 |
+
"learning_rate": 6.024691358024692e-05,
|
| 963 |
+
"loss": 0.489,
|
| 964 |
+
"step": 206
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 13.866666666666667,
|
| 968 |
+
"grad_norm": 4.0403971672058105,
|
| 969 |
+
"learning_rate": 5.975308641975309e-05,
|
| 970 |
+
"loss": 0.3524,
|
| 971 |
+
"step": 208
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 14.0,
|
| 975 |
+
"grad_norm": 11.723469734191895,
|
| 976 |
+
"learning_rate": 5.925925925925926e-05,
|
| 977 |
+
"loss": 0.6409,
|
| 978 |
+
"step": 210
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 14.0,
|
| 982 |
+
"eval_accuracy": 0.5984848484848485,
|
| 983 |
+
"eval_f1_macro": 0.5080833548412379,
|
| 984 |
+
"eval_f1_micro": 0.5984848484848485,
|
| 985 |
+
"eval_f1_weighted": 0.576454835403795,
|
| 986 |
+
"eval_loss": 1.4066194295883179,
|
| 987 |
+
"eval_precision_macro": 0.5193577256077255,
|
| 988 |
+
"eval_precision_micro": 0.5984848484848485,
|
| 989 |
+
"eval_precision_weighted": 0.5819911307127215,
|
| 990 |
+
"eval_recall_macro": 0.5231594860166289,
|
| 991 |
+
"eval_recall_micro": 0.5984848484848485,
|
| 992 |
+
"eval_recall_weighted": 0.5984848484848485,
|
| 993 |
+
"eval_runtime": 4.8101,
|
| 994 |
+
"eval_samples_per_second": 27.442,
|
| 995 |
+
"eval_steps_per_second": 1.039,
|
| 996 |
+
"step": 210
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 14.133333333333333,
|
| 1000 |
+
"grad_norm": 4.278630256652832,
|
| 1001 |
+
"learning_rate": 5.8765432098765437e-05,
|
| 1002 |
+
"loss": 0.1963,
|
| 1003 |
+
"step": 212
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 14.266666666666667,
|
| 1007 |
+
"grad_norm": 5.803009510040283,
|
| 1008 |
+
"learning_rate": 5.8271604938271607e-05,
|
| 1009 |
+
"loss": 0.4284,
|
| 1010 |
+
"step": 214
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 14.4,
|
| 1014 |
+
"grad_norm": 4.886916160583496,
|
| 1015 |
+
"learning_rate": 5.7777777777777776e-05,
|
| 1016 |
+
"loss": 0.3091,
|
| 1017 |
+
"step": 216
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 14.533333333333333,
|
| 1021 |
+
"grad_norm": 6.119672775268555,
|
| 1022 |
+
"learning_rate": 5.728395061728395e-05,
|
| 1023 |
+
"loss": 0.3287,
|
| 1024 |
+
"step": 218
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 14.666666666666666,
|
| 1028 |
+
"grad_norm": 7.14682149887085,
|
| 1029 |
+
"learning_rate": 5.679012345679012e-05,
|
| 1030 |
+
"loss": 0.2819,
|
| 1031 |
+
"step": 220
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 14.8,
|
| 1035 |
+
"grad_norm": 5.075103282928467,
|
| 1036 |
+
"learning_rate": 5.62962962962963e-05,
|
| 1037 |
+
"loss": 0.2101,
|
| 1038 |
+
"step": 222
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 14.933333333333334,
|
| 1042 |
+
"grad_norm": 4.5539045333862305,
|
| 1043 |
+
"learning_rate": 5.580246913580247e-05,
|
| 1044 |
+
"loss": 0.3206,
|
| 1045 |
+
"step": 224
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 15.0,
|
| 1049 |
+
"eval_accuracy": 0.5606060606060606,
|
| 1050 |
+
"eval_f1_macro": 0.5154896879386676,
|
| 1051 |
+
"eval_f1_micro": 0.5606060606060606,
|
| 1052 |
+
"eval_f1_weighted": 0.5520090359376074,
|
| 1053 |
+
"eval_loss": 1.3689966201782227,
|
| 1054 |
+
"eval_precision_macro": 0.6158199643493761,
|
| 1055 |
+
"eval_precision_micro": 0.5606060606060606,
|
| 1056 |
+
"eval_precision_weighted": 0.5889932074758278,
|
| 1057 |
+
"eval_recall_macro": 0.5170219198790628,
|
| 1058 |
+
"eval_recall_micro": 0.5606060606060606,
|
| 1059 |
+
"eval_recall_weighted": 0.5606060606060606,
|
| 1060 |
+
"eval_runtime": 2.0949,
|
| 1061 |
+
"eval_samples_per_second": 63.009,
|
| 1062 |
+
"eval_steps_per_second": 2.387,
|
| 1063 |
+
"step": 225
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 15.066666666666666,
|
| 1067 |
+
"grad_norm": 4.093947887420654,
|
| 1068 |
+
"learning_rate": 5.530864197530864e-05,
|
| 1069 |
+
"loss": 0.3352,
|
| 1070 |
+
"step": 226
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 15.2,
|
| 1074 |
+
"grad_norm": 5.242745876312256,
|
| 1075 |
+
"learning_rate": 5.4814814814814817e-05,
|
| 1076 |
+
"loss": 0.2066,
|
| 1077 |
+
"step": 228
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 15.333333333333334,
|
| 1081 |
+
"grad_norm": 5.613947868347168,
|
| 1082 |
+
"learning_rate": 5.4320987654320986e-05,
|
| 1083 |
+
"loss": 0.3504,
|
| 1084 |
+
"step": 230
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 15.466666666666667,
|
| 1088 |
+
"grad_norm": 3.4319839477539062,
|
| 1089 |
+
"learning_rate": 5.382716049382717e-05,
|
| 1090 |
+
"loss": 0.2294,
|
| 1091 |
+
"step": 232
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 15.6,
|
| 1095 |
+
"grad_norm": 6.01231575012207,
|
| 1096 |
+
"learning_rate": 5.333333333333333e-05,
|
| 1097 |
+
"loss": 0.2498,
|
| 1098 |
+
"step": 234
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 15.733333333333333,
|
| 1102 |
+
"grad_norm": 3.9071357250213623,
|
| 1103 |
+
"learning_rate": 5.28395061728395e-05,
|
| 1104 |
+
"loss": 0.2092,
|
| 1105 |
+
"step": 236
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 15.866666666666667,
|
| 1109 |
+
"grad_norm": 5.718769550323486,
|
| 1110 |
+
"learning_rate": 5.234567901234568e-05,
|
| 1111 |
+
"loss": 0.2223,
|
| 1112 |
+
"step": 238
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 16.0,
|
| 1116 |
+
"grad_norm": 4.071746349334717,
|
| 1117 |
+
"learning_rate": 5.185185185185185e-05,
|
| 1118 |
+
"loss": 0.1773,
|
| 1119 |
+
"step": 240
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 16.0,
|
| 1123 |
+
"eval_accuracy": 0.6515151515151515,
|
| 1124 |
+
"eval_f1_macro": 0.592019301793738,
|
| 1125 |
+
"eval_f1_micro": 0.6515151515151515,
|
| 1126 |
+
"eval_f1_weighted": 0.6407837434153223,
|
| 1127 |
+
"eval_loss": 1.2568100690841675,
|
| 1128 |
+
"eval_precision_macro": 0.6893528941196284,
|
| 1129 |
+
"eval_precision_micro": 0.6515151515151515,
|
| 1130 |
+
"eval_precision_weighted": 0.6623135907365115,
|
| 1131 |
+
"eval_recall_macro": 0.5842857142857143,
|
| 1132 |
+
"eval_recall_micro": 0.6515151515151515,
|
| 1133 |
+
"eval_recall_weighted": 0.6515151515151515,
|
| 1134 |
+
"eval_runtime": 1.9927,
|
| 1135 |
+
"eval_samples_per_second": 66.24,
|
| 1136 |
+
"eval_steps_per_second": 2.509,
|
| 1137 |
+
"step": 240
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 16.133333333333333,
|
| 1141 |
+
"grad_norm": 3.561516761779785,
|
| 1142 |
+
"learning_rate": 5.135802469135803e-05,
|
| 1143 |
+
"loss": 0.1696,
|
| 1144 |
+
"step": 242
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 16.266666666666666,
|
| 1148 |
+
"grad_norm": 1.3526779413223267,
|
| 1149 |
+
"learning_rate": 5.0864197530864197e-05,
|
| 1150 |
+
"loss": 0.0665,
|
| 1151 |
+
"step": 244
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 16.4,
|
| 1155 |
+
"grad_norm": 4.29080057144165,
|
| 1156 |
+
"learning_rate": 5.0370370370370366e-05,
|
| 1157 |
+
"loss": 0.195,
|
| 1158 |
+
"step": 246
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 16.533333333333335,
|
| 1162 |
+
"grad_norm": 6.229769706726074,
|
| 1163 |
+
"learning_rate": 4.987654320987655e-05,
|
| 1164 |
+
"loss": 0.2993,
|
| 1165 |
+
"step": 248
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 16.666666666666668,
|
| 1169 |
+
"grad_norm": 4.949665546417236,
|
| 1170 |
+
"learning_rate": 4.938271604938271e-05,
|
| 1171 |
+
"loss": 0.2081,
|
| 1172 |
+
"step": 250
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 16.8,
|
| 1176 |
+
"grad_norm": 6.123852252960205,
|
| 1177 |
+
"learning_rate": 4.888888888888889e-05,
|
| 1178 |
+
"loss": 0.212,
|
| 1179 |
+
"step": 252
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 16.933333333333334,
|
| 1183 |
+
"grad_norm": 4.0239105224609375,
|
| 1184 |
+
"learning_rate": 4.8395061728395067e-05,
|
| 1185 |
+
"loss": 0.3259,
|
| 1186 |
+
"step": 254
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 17.0,
|
| 1190 |
+
"eval_accuracy": 0.6060606060606061,
|
| 1191 |
+
"eval_f1_macro": 0.5467242234296787,
|
| 1192 |
+
"eval_f1_micro": 0.6060606060606061,
|
| 1193 |
+
"eval_f1_weighted": 0.5961390083174005,
|
| 1194 |
+
"eval_loss": 1.3405537605285645,
|
| 1195 |
+
"eval_precision_macro": 0.5614736217067472,
|
| 1196 |
+
"eval_precision_micro": 0.6060606060606061,
|
| 1197 |
+
"eval_precision_weighted": 0.6033042542530208,
|
| 1198 |
+
"eval_recall_macro": 0.5466817838246409,
|
| 1199 |
+
"eval_recall_micro": 0.6060606060606061,
|
| 1200 |
+
"eval_recall_weighted": 0.6060606060606061,
|
| 1201 |
+
"eval_runtime": 2.0502,
|
| 1202 |
+
"eval_samples_per_second": 64.382,
|
| 1203 |
+
"eval_steps_per_second": 2.439,
|
| 1204 |
+
"step": 255
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 17.066666666666666,
|
| 1208 |
+
"grad_norm": 1.4321271181106567,
|
| 1209 |
+
"learning_rate": 4.7901234567901237e-05,
|
| 1210 |
+
"loss": 0.055,
|
| 1211 |
+
"step": 256
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 17.2,
|
| 1215 |
+
"grad_norm": 2.13454008102417,
|
| 1216 |
+
"learning_rate": 4.740740740740741e-05,
|
| 1217 |
+
"loss": 0.1221,
|
| 1218 |
+
"step": 258
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 17.333333333333332,
|
| 1222 |
+
"grad_norm": 5.276524066925049,
|
| 1223 |
+
"learning_rate": 4.691358024691358e-05,
|
| 1224 |
+
"loss": 0.1417,
|
| 1225 |
+
"step": 260
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 17.466666666666665,
|
| 1229 |
+
"grad_norm": 3.8555052280426025,
|
| 1230 |
+
"learning_rate": 4.641975308641975e-05,
|
| 1231 |
+
"loss": 0.2943,
|
| 1232 |
+
"step": 262
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 17.6,
|
| 1236 |
+
"grad_norm": 4.094534873962402,
|
| 1237 |
+
"learning_rate": 4.592592592592593e-05,
|
| 1238 |
+
"loss": 0.2206,
|
| 1239 |
+
"step": 264
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 17.733333333333334,
|
| 1243 |
+
"grad_norm": 4.184159278869629,
|
| 1244 |
+
"learning_rate": 4.54320987654321e-05,
|
| 1245 |
+
"loss": 0.1565,
|
| 1246 |
+
"step": 266
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 17.866666666666667,
|
| 1250 |
+
"grad_norm": 5.283144474029541,
|
| 1251 |
+
"learning_rate": 4.493827160493828e-05,
|
| 1252 |
+
"loss": 0.1427,
|
| 1253 |
+
"step": 268
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 18.0,
|
| 1257 |
+
"grad_norm": 3.6470813751220703,
|
| 1258 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 1259 |
+
"loss": 0.1123,
|
| 1260 |
+
"step": 270
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 18.0,
|
| 1264 |
+
"eval_accuracy": 0.6363636363636364,
|
| 1265 |
+
"eval_f1_macro": 0.5867719657675725,
|
| 1266 |
+
"eval_f1_micro": 0.6363636363636364,
|
| 1267 |
+
"eval_f1_weighted": 0.6305501232595613,
|
| 1268 |
+
"eval_loss": 1.376707911491394,
|
| 1269 |
+
"eval_precision_macro": 0.6257631257631259,
|
| 1270 |
+
"eval_precision_micro": 0.6363636363636364,
|
| 1271 |
+
"eval_precision_weighted": 0.6413447663447664,
|
| 1272 |
+
"eval_recall_macro": 0.5785109599395314,
|
| 1273 |
+
"eval_recall_micro": 0.6363636363636364,
|
| 1274 |
+
"eval_recall_weighted": 0.6363636363636364,
|
| 1275 |
+
"eval_runtime": 1.992,
|
| 1276 |
+
"eval_samples_per_second": 66.266,
|
| 1277 |
+
"eval_steps_per_second": 2.51,
|
| 1278 |
+
"step": 270
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 18.133333333333333,
|
| 1282 |
+
"grad_norm": 3.1710643768310547,
|
| 1283 |
+
"learning_rate": 4.3950617283950617e-05,
|
| 1284 |
+
"loss": 0.1219,
|
| 1285 |
+
"step": 272
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 18.266666666666666,
|
| 1289 |
+
"grad_norm": 7.098196506500244,
|
| 1290 |
+
"learning_rate": 4.345679012345679e-05,
|
| 1291 |
+
"loss": 0.1588,
|
| 1292 |
+
"step": 274
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 18.4,
|
| 1296 |
+
"grad_norm": 1.8567241430282593,
|
| 1297 |
+
"learning_rate": 4.296296296296296e-05,
|
| 1298 |
+
"loss": 0.1043,
|
| 1299 |
+
"step": 276
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 18.533333333333335,
|
| 1303 |
+
"grad_norm": 2.1221156120300293,
|
| 1304 |
+
"learning_rate": 4.246913580246914e-05,
|
| 1305 |
+
"loss": 0.0748,
|
| 1306 |
+
"step": 278
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 18.666666666666668,
|
| 1310 |
+
"grad_norm": 3.03196120262146,
|
| 1311 |
+
"learning_rate": 4.197530864197531e-05,
|
| 1312 |
+
"loss": 0.1148,
|
| 1313 |
+
"step": 280
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 18.8,
|
| 1317 |
+
"grad_norm": 1.7942876815795898,
|
| 1318 |
+
"learning_rate": 4.148148148148148e-05,
|
| 1319 |
+
"loss": 0.0679,
|
| 1320 |
+
"step": 282
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 18.933333333333334,
|
| 1324 |
+
"grad_norm": 4.499013900756836,
|
| 1325 |
+
"learning_rate": 4.0987654320987657e-05,
|
| 1326 |
+
"loss": 0.1129,
|
| 1327 |
+
"step": 284
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 19.0,
|
| 1331 |
+
"eval_accuracy": 0.6439393939393939,
|
| 1332 |
+
"eval_f1_macro": 0.587916778045086,
|
| 1333 |
+
"eval_f1_micro": 0.6439393939393939,
|
| 1334 |
+
"eval_f1_weighted": 0.6305576751206262,
|
| 1335 |
+
"eval_loss": 1.4679865837097168,
|
| 1336 |
+
"eval_precision_macro": 0.6809288563910413,
|
| 1337 |
+
"eval_precision_micro": 0.6439393939393939,
|
| 1338 |
+
"eval_precision_weighted": 0.6932697872537444,
|
| 1339 |
+
"eval_recall_macro": 0.5806046863189721,
|
| 1340 |
+
"eval_recall_micro": 0.6439393939393939,
|
| 1341 |
+
"eval_recall_weighted": 0.6439393939393939,
|
| 1342 |
+
"eval_runtime": 1.9847,
|
| 1343 |
+
"eval_samples_per_second": 66.508,
|
| 1344 |
+
"eval_steps_per_second": 2.519,
|
| 1345 |
+
"step": 285
|
| 1346 |
+
},
|
| 1347 |
+
{
|
| 1348 |
+
"epoch": 19.066666666666666,
|
| 1349 |
+
"grad_norm": 2.631176233291626,
|
| 1350 |
+
"learning_rate": 4.049382716049383e-05,
|
| 1351 |
+
"loss": 0.1028,
|
| 1352 |
+
"step": 286
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 19.2,
|
| 1356 |
+
"grad_norm": 4.930914402008057,
|
| 1357 |
+
"learning_rate": 4e-05,
|
| 1358 |
+
"loss": 0.2555,
|
| 1359 |
+
"step": 288
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 19.333333333333332,
|
| 1363 |
+
"grad_norm": 3.355149745941162,
|
| 1364 |
+
"learning_rate": 3.950617283950617e-05,
|
| 1365 |
+
"loss": 0.0792,
|
| 1366 |
+
"step": 290
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 19.466666666666665,
|
| 1370 |
+
"grad_norm": 2.2780933380126953,
|
| 1371 |
+
"learning_rate": 3.901234567901234e-05,
|
| 1372 |
+
"loss": 0.0595,
|
| 1373 |
+
"step": 292
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 19.6,
|
| 1377 |
+
"grad_norm": 4.880768299102783,
|
| 1378 |
+
"learning_rate": 3.851851851851852e-05,
|
| 1379 |
+
"loss": 0.0756,
|
| 1380 |
+
"step": 294
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 19.733333333333334,
|
| 1384 |
+
"grad_norm": 2.175165891647339,
|
| 1385 |
+
"learning_rate": 3.80246913580247e-05,
|
| 1386 |
+
"loss": 0.1077,
|
| 1387 |
+
"step": 296
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 19.866666666666667,
|
| 1391 |
+
"grad_norm": 2.6557981967926025,
|
| 1392 |
+
"learning_rate": 3.7530864197530867e-05,
|
| 1393 |
+
"loss": 0.1094,
|
| 1394 |
+
"step": 298
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 20.0,
|
| 1398 |
+
"grad_norm": 1.2508912086486816,
|
| 1399 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 1400 |
+
"loss": 0.0651,
|
| 1401 |
+
"step": 300
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 20.0,
|
| 1405 |
+
"eval_accuracy": 0.6893939393939394,
|
| 1406 |
+
"eval_f1_macro": 0.6655257312106627,
|
| 1407 |
+
"eval_f1_micro": 0.6893939393939394,
|
| 1408 |
+
"eval_f1_weighted": 0.687595503348928,
|
| 1409 |
+
"eval_loss": 1.4981398582458496,
|
| 1410 |
+
"eval_precision_macro": 0.7114991648833447,
|
| 1411 |
+
"eval_precision_micro": 0.6893939393939394,
|
| 1412 |
+
"eval_precision_weighted": 0.7224498247915767,
|
| 1413 |
+
"eval_recall_macro": 0.6510808767951625,
|
| 1414 |
+
"eval_recall_micro": 0.6893939393939394,
|
| 1415 |
+
"eval_recall_weighted": 0.6893939393939394,
|
| 1416 |
+
"eval_runtime": 1.9861,
|
| 1417 |
+
"eval_samples_per_second": 66.462,
|
| 1418 |
+
"eval_steps_per_second": 2.517,
|
| 1419 |
+
"step": 300
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 20.133333333333333,
|
| 1423 |
+
"grad_norm": 5.263727188110352,
|
| 1424 |
+
"learning_rate": 3.654320987654321e-05,
|
| 1425 |
+
"loss": 0.075,
|
| 1426 |
+
"step": 302
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 20.266666666666666,
|
| 1430 |
+
"grad_norm": 4.619281768798828,
|
| 1431 |
+
"learning_rate": 3.604938271604938e-05,
|
| 1432 |
+
"loss": 0.1319,
|
| 1433 |
+
"step": 304
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 20.4,
|
| 1437 |
+
"grad_norm": 1.0995675325393677,
|
| 1438 |
+
"learning_rate": 3.555555555555556e-05,
|
| 1439 |
+
"loss": 0.0366,
|
| 1440 |
+
"step": 306
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 20.533333333333335,
|
| 1444 |
+
"grad_norm": 4.2385663986206055,
|
| 1445 |
+
"learning_rate": 3.506172839506173e-05,
|
| 1446 |
+
"loss": 0.1331,
|
| 1447 |
+
"step": 308
|
| 1448 |
+
},
|
| 1449 |
+
{
|
| 1450 |
+
"epoch": 20.666666666666668,
|
| 1451 |
+
"grad_norm": 2.6913745403289795,
|
| 1452 |
+
"learning_rate": 3.45679012345679e-05,
|
| 1453 |
+
"loss": 0.0894,
|
| 1454 |
+
"step": 310
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 20.8,
|
| 1458 |
+
"grad_norm": 4.785970687866211,
|
| 1459 |
+
"learning_rate": 3.4074074074074077e-05,
|
| 1460 |
+
"loss": 0.0756,
|
| 1461 |
+
"step": 312
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 20.933333333333334,
|
| 1465 |
+
"grad_norm": 1.5702877044677734,
|
| 1466 |
+
"learning_rate": 3.3580246913580247e-05,
|
| 1467 |
+
"loss": 0.0685,
|
| 1468 |
+
"step": 314
|
| 1469 |
+
},
|
| 1470 |
+
{
|
| 1471 |
+
"epoch": 21.0,
|
| 1472 |
+
"eval_accuracy": 0.6515151515151515,
|
| 1473 |
+
"eval_f1_macro": 0.6091138915880551,
|
| 1474 |
+
"eval_f1_micro": 0.6515151515151515,
|
| 1475 |
+
"eval_f1_weighted": 0.6494256262321655,
|
| 1476 |
+
"eval_loss": 1.4620611667633057,
|
| 1477 |
+
"eval_precision_macro": 0.630280884283538,
|
| 1478 |
+
"eval_precision_micro": 0.6515151515151515,
|
| 1479 |
+
"eval_precision_weighted": 0.664075183502428,
|
| 1480 |
+
"eval_recall_macro": 0.6039682539682539,
|
| 1481 |
+
"eval_recall_micro": 0.6515151515151515,
|
| 1482 |
+
"eval_recall_weighted": 0.6515151515151515,
|
| 1483 |
+
"eval_runtime": 2.0276,
|
| 1484 |
+
"eval_samples_per_second": 65.103,
|
| 1485 |
+
"eval_steps_per_second": 2.466,
|
| 1486 |
+
"step": 315
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 21.066666666666666,
|
| 1490 |
+
"grad_norm": 0.6037698984146118,
|
| 1491 |
+
"learning_rate": 3.308641975308642e-05,
|
| 1492 |
+
"loss": 0.0537,
|
| 1493 |
+
"step": 316
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 21.2,
|
| 1497 |
+
"grad_norm": 0.877955436706543,
|
| 1498 |
+
"learning_rate": 3.25925925925926e-05,
|
| 1499 |
+
"loss": 0.0283,
|
| 1500 |
+
"step": 318
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 21.333333333333332,
|
| 1504 |
+
"grad_norm": 4.185865879058838,
|
| 1505 |
+
"learning_rate": 3.209876543209876e-05,
|
| 1506 |
+
"loss": 0.1153,
|
| 1507 |
+
"step": 320
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 21.466666666666665,
|
| 1511 |
+
"grad_norm": 0.7465834021568298,
|
| 1512 |
+
"learning_rate": 3.160493827160494e-05,
|
| 1513 |
+
"loss": 0.0311,
|
| 1514 |
+
"step": 322
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 21.6,
|
| 1518 |
+
"grad_norm": 1.4049850702285767,
|
| 1519 |
+
"learning_rate": 3.111111111111111e-05,
|
| 1520 |
+
"loss": 0.0641,
|
| 1521 |
+
"step": 324
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 21.733333333333334,
|
| 1525 |
+
"grad_norm": 1.6191234588623047,
|
| 1526 |
+
"learning_rate": 3.061728395061729e-05,
|
| 1527 |
+
"loss": 0.0417,
|
| 1528 |
+
"step": 326
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 21.866666666666667,
|
| 1532 |
+
"grad_norm": 1.2088876962661743,
|
| 1533 |
+
"learning_rate": 3.012345679012346e-05,
|
| 1534 |
+
"loss": 0.0314,
|
| 1535 |
+
"step": 328
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 22.0,
|
| 1539 |
+
"grad_norm": 0.7652052640914917,
|
| 1540 |
+
"learning_rate": 2.962962962962963e-05,
|
| 1541 |
+
"loss": 0.1469,
|
| 1542 |
+
"step": 330
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 22.0,
|
| 1546 |
+
"eval_accuracy": 0.6212121212121212,
|
| 1547 |
+
"eval_f1_macro": 0.5330299221627766,
|
| 1548 |
+
"eval_f1_micro": 0.6212121212121212,
|
| 1549 |
+
"eval_f1_weighted": 0.604041002442862,
|
| 1550 |
+
"eval_loss": 1.534732699394226,
|
| 1551 |
+
"eval_precision_macro": 0.5476940619507992,
|
| 1552 |
+
"eval_precision_micro": 0.6212121212121212,
|
| 1553 |
+
"eval_precision_weighted": 0.6148931558944467,
|
| 1554 |
+
"eval_recall_macro": 0.5439984882842026,
|
| 1555 |
+
"eval_recall_micro": 0.6212121212121212,
|
| 1556 |
+
"eval_recall_weighted": 0.6212121212121212,
|
| 1557 |
+
"eval_runtime": 1.9747,
|
| 1558 |
+
"eval_samples_per_second": 66.844,
|
| 1559 |
+
"eval_steps_per_second": 2.532,
|
| 1560 |
+
"step": 330
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 22.133333333333333,
|
| 1564 |
+
"grad_norm": 3.304185152053833,
|
| 1565 |
+
"learning_rate": 2.9135802469135803e-05,
|
| 1566 |
+
"loss": 0.0456,
|
| 1567 |
+
"step": 332
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 22.266666666666666,
|
| 1571 |
+
"grad_norm": 2.3118255138397217,
|
| 1572 |
+
"learning_rate": 2.8641975308641977e-05,
|
| 1573 |
+
"loss": 0.0377,
|
| 1574 |
+
"step": 334
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 22.4,
|
| 1578 |
+
"grad_norm": 2.3639698028564453,
|
| 1579 |
+
"learning_rate": 2.814814814814815e-05,
|
| 1580 |
+
"loss": 0.0708,
|
| 1581 |
+
"step": 336
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 22.533333333333335,
|
| 1585 |
+
"grad_norm": 1.741746187210083,
|
| 1586 |
+
"learning_rate": 2.765432098765432e-05,
|
| 1587 |
+
"loss": 0.0353,
|
| 1588 |
+
"step": 338
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 22.666666666666668,
|
| 1592 |
+
"grad_norm": 0.6108101010322571,
|
| 1593 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 1594 |
+
"loss": 0.0531,
|
| 1595 |
+
"step": 340
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 22.8,
|
| 1599 |
+
"grad_norm": 2.961045503616333,
|
| 1600 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 1601 |
+
"loss": 0.0394,
|
| 1602 |
+
"step": 342
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 22.933333333333334,
|
| 1606 |
+
"grad_norm": 1.7298003435134888,
|
| 1607 |
+
"learning_rate": 2.617283950617284e-05,
|
| 1608 |
+
"loss": 0.0289,
|
| 1609 |
+
"step": 344
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 23.0,
|
| 1613 |
+
"eval_accuracy": 0.6287878787878788,
|
| 1614 |
+
"eval_f1_macro": 0.5465784005632545,
|
| 1615 |
+
"eval_f1_micro": 0.6287878787878788,
|
| 1616 |
+
"eval_f1_weighted": 0.6179920372130975,
|
| 1617 |
+
"eval_loss": 1.5417176485061646,
|
| 1618 |
+
"eval_precision_macro": 0.5409361471861472,
|
| 1619 |
+
"eval_precision_micro": 0.6287878787878788,
|
| 1620 |
+
"eval_precision_weighted": 0.610816976584022,
|
| 1621 |
+
"eval_recall_macro": 0.5549206349206349,
|
| 1622 |
+
"eval_recall_micro": 0.6287878787878788,
|
| 1623 |
+
"eval_recall_weighted": 0.6287878787878788,
|
| 1624 |
+
"eval_runtime": 1.9902,
|
| 1625 |
+
"eval_samples_per_second": 66.326,
|
| 1626 |
+
"eval_steps_per_second": 2.512,
|
| 1627 |
+
"step": 345
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 23.066666666666666,
|
| 1631 |
+
"grad_norm": 0.7690654397010803,
|
| 1632 |
+
"learning_rate": 2.5679012345679017e-05,
|
| 1633 |
+
"loss": 0.0458,
|
| 1634 |
+
"step": 346
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 23.2,
|
| 1638 |
+
"grad_norm": 3.320651054382324,
|
| 1639 |
+
"learning_rate": 2.5185185185185183e-05,
|
| 1640 |
+
"loss": 0.0804,
|
| 1641 |
+
"step": 348
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 23.333333333333332,
|
| 1645 |
+
"grad_norm": 2.0301012992858887,
|
| 1646 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 1647 |
+
"loss": 0.0279,
|
| 1648 |
+
"step": 350
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 23.466666666666665,
|
| 1652 |
+
"grad_norm": 0.4531901478767395,
|
| 1653 |
+
"learning_rate": 2.4197530864197533e-05,
|
| 1654 |
+
"loss": 0.0139,
|
| 1655 |
+
"step": 352
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 23.6,
|
| 1659 |
+
"grad_norm": 2.56703519821167,
|
| 1660 |
+
"learning_rate": 2.3703703703703707e-05,
|
| 1661 |
+
"loss": 0.0783,
|
| 1662 |
+
"step": 354
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 23.733333333333334,
|
| 1666 |
+
"grad_norm": 0.20635652542114258,
|
| 1667 |
+
"learning_rate": 2.3209876543209877e-05,
|
| 1668 |
+
"loss": 0.012,
|
| 1669 |
+
"step": 356
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 23.866666666666667,
|
| 1673 |
+
"grad_norm": 0.5930025577545166,
|
| 1674 |
+
"learning_rate": 2.271604938271605e-05,
|
| 1675 |
+
"loss": 0.0145,
|
| 1676 |
+
"step": 358
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 24.0,
|
| 1680 |
+
"grad_norm": 0.24041523039340973,
|
| 1681 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1682 |
+
"loss": 0.01,
|
| 1683 |
+
"step": 360
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 24.0,
|
| 1687 |
+
"eval_accuracy": 0.6363636363636364,
|
| 1688 |
+
"eval_f1_macro": 0.5474889044983636,
|
| 1689 |
+
"eval_f1_micro": 0.6363636363636364,
|
| 1690 |
+
"eval_f1_weighted": 0.6187343775995573,
|
| 1691 |
+
"eval_loss": 1.5670151710510254,
|
| 1692 |
+
"eval_precision_macro": 0.5434552419168567,
|
| 1693 |
+
"eval_precision_micro": 0.6363636363636364,
|
| 1694 |
+
"eval_precision_weighted": 0.6103857259761386,
|
| 1695 |
+
"eval_recall_macro": 0.5594179894179894,
|
| 1696 |
+
"eval_recall_micro": 0.6363636363636364,
|
| 1697 |
+
"eval_recall_weighted": 0.6363636363636364,
|
| 1698 |
+
"eval_runtime": 1.9405,
|
| 1699 |
+
"eval_samples_per_second": 68.023,
|
| 1700 |
+
"eval_steps_per_second": 2.577,
|
| 1701 |
+
"step": 360
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 24.133333333333333,
|
| 1705 |
+
"grad_norm": 0.21558411419391632,
|
| 1706 |
+
"learning_rate": 2.1728395061728397e-05,
|
| 1707 |
+
"loss": 0.0102,
|
| 1708 |
+
"step": 362
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 24.266666666666666,
|
| 1712 |
+
"grad_norm": 3.2394814491271973,
|
| 1713 |
+
"learning_rate": 2.123456790123457e-05,
|
| 1714 |
+
"loss": 0.0218,
|
| 1715 |
+
"step": 364
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 24.4,
|
| 1719 |
+
"grad_norm": 3.6115405559539795,
|
| 1720 |
+
"learning_rate": 2.074074074074074e-05,
|
| 1721 |
+
"loss": 0.1149,
|
| 1722 |
+
"step": 366
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 24.533333333333335,
|
| 1726 |
+
"grad_norm": 0.1589735597372055,
|
| 1727 |
+
"learning_rate": 2.0246913580246917e-05,
|
| 1728 |
+
"loss": 0.0082,
|
| 1729 |
+
"step": 368
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 24.666666666666668,
|
| 1733 |
+
"grad_norm": 1.3840848207473755,
|
| 1734 |
+
"learning_rate": 1.9753086419753087e-05,
|
| 1735 |
+
"loss": 0.0174,
|
| 1736 |
+
"step": 370
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 24.8,
|
| 1740 |
+
"grad_norm": 3.772754192352295,
|
| 1741 |
+
"learning_rate": 1.925925925925926e-05,
|
| 1742 |
+
"loss": 0.043,
|
| 1743 |
+
"step": 372
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 24.933333333333334,
|
| 1747 |
+
"grad_norm": 0.41601723432540894,
|
| 1748 |
+
"learning_rate": 1.8765432098765433e-05,
|
| 1749 |
+
"loss": 0.035,
|
| 1750 |
+
"step": 374
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 25.0,
|
| 1754 |
+
"eval_accuracy": 0.6363636363636364,
|
| 1755 |
+
"eval_f1_macro": 0.5529395694676043,
|
| 1756 |
+
"eval_f1_micro": 0.6363636363636364,
|
| 1757 |
+
"eval_f1_weighted": 0.6209326623035122,
|
| 1758 |
+
"eval_loss": 1.6037245988845825,
|
| 1759 |
+
"eval_precision_macro": 0.5470247238680418,
|
| 1760 |
+
"eval_precision_micro": 0.6363636363636364,
|
| 1761 |
+
"eval_precision_weighted": 0.6156263091746962,
|
| 1762 |
+
"eval_recall_macro": 0.5679213907785335,
|
| 1763 |
+
"eval_recall_micro": 0.6363636363636364,
|
| 1764 |
+
"eval_recall_weighted": 0.6363636363636364,
|
| 1765 |
+
"eval_runtime": 1.9551,
|
| 1766 |
+
"eval_samples_per_second": 67.515,
|
| 1767 |
+
"eval_steps_per_second": 2.557,
|
| 1768 |
+
"step": 375
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 25.066666666666666,
|
| 1772 |
+
"grad_norm": 0.4554837942123413,
|
| 1773 |
+
"learning_rate": 1.8271604938271607e-05,
|
| 1774 |
+
"loss": 0.0636,
|
| 1775 |
+
"step": 376
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 25.2,
|
| 1779 |
+
"grad_norm": 4.667645454406738,
|
| 1780 |
+
"learning_rate": 1.777777777777778e-05,
|
| 1781 |
+
"loss": 0.0685,
|
| 1782 |
+
"step": 378
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 25.333333333333332,
|
| 1786 |
+
"grad_norm": 6.68064022064209,
|
| 1787 |
+
"learning_rate": 1.728395061728395e-05,
|
| 1788 |
+
"loss": 0.0919,
|
| 1789 |
+
"step": 380
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 25.466666666666665,
|
| 1793 |
+
"grad_norm": 0.2510056793689728,
|
| 1794 |
+
"learning_rate": 1.6790123456790123e-05,
|
| 1795 |
+
"loss": 0.0111,
|
| 1796 |
+
"step": 382
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 25.6,
|
| 1800 |
+
"grad_norm": 0.6245520114898682,
|
| 1801 |
+
"learning_rate": 1.62962962962963e-05,
|
| 1802 |
+
"loss": 0.0134,
|
| 1803 |
+
"step": 384
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 25.733333333333334,
|
| 1807 |
+
"grad_norm": 2.165201187133789,
|
| 1808 |
+
"learning_rate": 1.580246913580247e-05,
|
| 1809 |
+
"loss": 0.0271,
|
| 1810 |
+
"step": 386
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 25.866666666666667,
|
| 1814 |
+
"grad_norm": 0.24112091958522797,
|
| 1815 |
+
"learning_rate": 1.5308641975308643e-05,
|
| 1816 |
+
"loss": 0.0105,
|
| 1817 |
+
"step": 388
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 26.0,
|
| 1821 |
+
"grad_norm": 0.377363383769989,
|
| 1822 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 1823 |
+
"loss": 0.0109,
|
| 1824 |
+
"step": 390
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 26.0,
|
| 1828 |
+
"eval_accuracy": 0.6212121212121212,
|
| 1829 |
+
"eval_f1_macro": 0.5896814040471776,
|
| 1830 |
+
"eval_f1_micro": 0.6212121212121212,
|
| 1831 |
+
"eval_f1_weighted": 0.6203213160225189,
|
| 1832 |
+
"eval_loss": 1.6751586198806763,
|
| 1833 |
+
"eval_precision_macro": 0.6144605795534588,
|
| 1834 |
+
"eval_precision_micro": 0.6212121212121212,
|
| 1835 |
+
"eval_precision_weighted": 0.6527441598649029,
|
| 1836 |
+
"eval_recall_macro": 0.5999697656840514,
|
| 1837 |
+
"eval_recall_micro": 0.6212121212121212,
|
| 1838 |
+
"eval_recall_weighted": 0.6212121212121212,
|
| 1839 |
+
"eval_runtime": 1.9656,
|
| 1840 |
+
"eval_samples_per_second": 67.154,
|
| 1841 |
+
"eval_steps_per_second": 2.544,
|
| 1842 |
+
"step": 390
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 26.133333333333333,
|
| 1846 |
+
"grad_norm": 0.3774866461753845,
|
| 1847 |
+
"learning_rate": 1.4320987654320988e-05,
|
| 1848 |
+
"loss": 0.0097,
|
| 1849 |
+
"step": 392
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 26.266666666666666,
|
| 1853 |
+
"grad_norm": 3.956695079803467,
|
| 1854 |
+
"learning_rate": 1.382716049382716e-05,
|
| 1855 |
+
"loss": 0.0233,
|
| 1856 |
+
"step": 394
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 26.4,
|
| 1860 |
+
"grad_norm": 0.5877533555030823,
|
| 1861 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 1862 |
+
"loss": 0.0157,
|
| 1863 |
+
"step": 396
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 26.533333333333335,
|
| 1867 |
+
"grad_norm": 1.2962318658828735,
|
| 1868 |
+
"learning_rate": 1.2839506172839508e-05,
|
| 1869 |
+
"loss": 0.0249,
|
| 1870 |
+
"step": 398
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 26.666666666666668,
|
| 1874 |
+
"grad_norm": 2.2431485652923584,
|
| 1875 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 1876 |
+
"loss": 0.0224,
|
| 1877 |
+
"step": 400
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 26.8,
|
| 1881 |
+
"grad_norm": 0.21492817997932434,
|
| 1882 |
+
"learning_rate": 1.1851851851851853e-05,
|
| 1883 |
+
"loss": 0.0117,
|
| 1884 |
+
"step": 402
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 26.933333333333334,
|
| 1888 |
+
"grad_norm": 0.4237399697303772,
|
| 1889 |
+
"learning_rate": 1.1358024691358025e-05,
|
| 1890 |
+
"loss": 0.038,
|
| 1891 |
+
"step": 404
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 27.0,
|
| 1895 |
+
"eval_accuracy": 0.6136363636363636,
|
| 1896 |
+
"eval_f1_macro": 0.5343822919199936,
|
| 1897 |
+
"eval_f1_micro": 0.6136363636363636,
|
| 1898 |
+
"eval_f1_weighted": 0.6008425380028616,
|
| 1899 |
+
"eval_loss": 1.672375202178955,
|
| 1900 |
+
"eval_precision_macro": 0.5331553830282576,
|
| 1901 |
+
"eval_precision_micro": 0.6136363636363636,
|
| 1902 |
+
"eval_precision_weighted": 0.6004965634415023,
|
| 1903 |
+
"eval_recall_macro": 0.546832955404384,
|
| 1904 |
+
"eval_recall_micro": 0.6136363636363636,
|
| 1905 |
+
"eval_recall_weighted": 0.6136363636363636,
|
| 1906 |
+
"eval_runtime": 1.9801,
|
| 1907 |
+
"eval_samples_per_second": 66.662,
|
| 1908 |
+
"eval_steps_per_second": 2.525,
|
| 1909 |
+
"step": 405
|
| 1910 |
+
},
|
| 1911 |
+
{
|
| 1912 |
+
"epoch": 27.066666666666666,
|
| 1913 |
+
"grad_norm": 1.5725435018539429,
|
| 1914 |
+
"learning_rate": 1.0864197530864198e-05,
|
| 1915 |
+
"loss": 0.0149,
|
| 1916 |
+
"step": 406
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"epoch": 27.2,
|
| 1920 |
+
"grad_norm": 0.13784648478031158,
|
| 1921 |
+
"learning_rate": 1.037037037037037e-05,
|
| 1922 |
+
"loss": 0.0092,
|
| 1923 |
+
"step": 408
|
| 1924 |
+
},
|
| 1925 |
+
{
|
| 1926 |
+
"epoch": 27.333333333333332,
|
| 1927 |
+
"grad_norm": 0.09840863198041916,
|
| 1928 |
+
"learning_rate": 9.876543209876543e-06,
|
| 1929 |
+
"loss": 0.008,
|
| 1930 |
+
"step": 410
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 27.466666666666665,
|
| 1934 |
+
"grad_norm": 0.8349915146827698,
|
| 1935 |
+
"learning_rate": 9.382716049382717e-06,
|
| 1936 |
+
"loss": 0.0206,
|
| 1937 |
+
"step": 412
|
| 1938 |
+
},
|
| 1939 |
+
{
|
| 1940 |
+
"epoch": 27.6,
|
| 1941 |
+
"grad_norm": 0.33149102330207825,
|
| 1942 |
+
"learning_rate": 8.88888888888889e-06,
|
| 1943 |
+
"loss": 0.0173,
|
| 1944 |
+
"step": 414
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 27.733333333333334,
|
| 1948 |
+
"grad_norm": 0.3867279589176178,
|
| 1949 |
+
"learning_rate": 8.395061728395062e-06,
|
| 1950 |
+
"loss": 0.0093,
|
| 1951 |
+
"step": 416
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 27.866666666666667,
|
| 1955 |
+
"grad_norm": 1.726897120475769,
|
| 1956 |
+
"learning_rate": 7.901234567901235e-06,
|
| 1957 |
+
"loss": 0.0214,
|
| 1958 |
+
"step": 418
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 28.0,
|
| 1962 |
+
"grad_norm": 0.19306233525276184,
|
| 1963 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 1964 |
+
"loss": 0.0116,
|
| 1965 |
+
"step": 420
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 28.0,
|
| 1969 |
+
"eval_accuracy": 0.6212121212121212,
|
| 1970 |
+
"eval_f1_macro": 0.5383730158730159,
|
| 1971 |
+
"eval_f1_micro": 0.6212121212121212,
|
| 1972 |
+
"eval_f1_weighted": 0.609029280904281,
|
| 1973 |
+
"eval_loss": 1.6251877546310425,
|
| 1974 |
+
"eval_precision_macro": 0.533696432596027,
|
| 1975 |
+
"eval_precision_micro": 0.6212121212121212,
|
| 1976 |
+
"eval_precision_weighted": 0.6033010121498966,
|
| 1977 |
+
"eval_recall_macro": 0.5490778533635676,
|
| 1978 |
+
"eval_recall_micro": 0.6212121212121212,
|
| 1979 |
+
"eval_recall_weighted": 0.6212121212121212,
|
| 1980 |
+
"eval_runtime": 1.9285,
|
| 1981 |
+
"eval_samples_per_second": 68.448,
|
| 1982 |
+
"eval_steps_per_second": 2.593,
|
| 1983 |
+
"step": 420
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 28.133333333333333,
|
| 1987 |
+
"grad_norm": 1.669783115386963,
|
| 1988 |
+
"learning_rate": 6.91358024691358e-06,
|
| 1989 |
+
"loss": 0.0318,
|
| 1990 |
+
"step": 422
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 28.266666666666666,
|
| 1994 |
+
"grad_norm": 0.6250646114349365,
|
| 1995 |
+
"learning_rate": 6.419753086419754e-06,
|
| 1996 |
+
"loss": 0.0195,
|
| 1997 |
+
"step": 424
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 28.4,
|
| 2001 |
+
"grad_norm": 0.4752732813358307,
|
| 2002 |
+
"learning_rate": 5.925925925925927e-06,
|
| 2003 |
+
"loss": 0.0124,
|
| 2004 |
+
"step": 426
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 28.533333333333335,
|
| 2008 |
+
"grad_norm": 0.16341274976730347,
|
| 2009 |
+
"learning_rate": 5.432098765432099e-06,
|
| 2010 |
+
"loss": 0.0065,
|
| 2011 |
+
"step": 428
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 28.666666666666668,
|
| 2015 |
+
"grad_norm": 0.08904340863227844,
|
| 2016 |
+
"learning_rate": 4.938271604938272e-06,
|
| 2017 |
+
"loss": 0.0062,
|
| 2018 |
+
"step": 430
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 28.8,
|
| 2022 |
+
"grad_norm": 0.24332502484321594,
|
| 2023 |
+
"learning_rate": 4.444444444444445e-06,
|
| 2024 |
+
"loss": 0.0055,
|
| 2025 |
+
"step": 432
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 28.933333333333334,
|
| 2029 |
+
"grad_norm": 0.47205692529678345,
|
| 2030 |
+
"learning_rate": 3.9506172839506175e-06,
|
| 2031 |
+
"loss": 0.006,
|
| 2032 |
+
"step": 434
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 29.0,
|
| 2036 |
+
"eval_accuracy": 0.6363636363636364,
|
| 2037 |
+
"eval_f1_macro": 0.557191887992969,
|
| 2038 |
+
"eval_f1_micro": 0.6363636363636364,
|
| 2039 |
+
"eval_f1_weighted": 0.6294141170899599,
|
| 2040 |
+
"eval_loss": 1.597952961921692,
|
| 2041 |
+
"eval_precision_macro": 0.5529214559386972,
|
| 2042 |
+
"eval_precision_micro": 0.6363636363636364,
|
| 2043 |
+
"eval_precision_weighted": 0.6245954516428655,
|
| 2044 |
+
"eval_recall_macro": 0.563363567649282,
|
| 2045 |
+
"eval_recall_micro": 0.6363636363636364,
|
| 2046 |
+
"eval_recall_weighted": 0.6363636363636364,
|
| 2047 |
+
"eval_runtime": 1.9083,
|
| 2048 |
+
"eval_samples_per_second": 69.172,
|
| 2049 |
+
"eval_steps_per_second": 2.62,
|
| 2050 |
+
"step": 435
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 29.066666666666666,
|
| 2054 |
+
"grad_norm": 0.27642032504081726,
|
| 2055 |
+
"learning_rate": 3.45679012345679e-06,
|
| 2056 |
+
"loss": 0.0162,
|
| 2057 |
+
"step": 436
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 29.2,
|
| 2061 |
+
"grad_norm": 0.9449041485786438,
|
| 2062 |
+
"learning_rate": 2.9629629629629633e-06,
|
| 2063 |
+
"loss": 0.0088,
|
| 2064 |
+
"step": 438
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 29.333333333333332,
|
| 2068 |
+
"grad_norm": 0.14337310194969177,
|
| 2069 |
+
"learning_rate": 2.469135802469136e-06,
|
| 2070 |
+
"loss": 0.0193,
|
| 2071 |
+
"step": 440
|
| 2072 |
+
},
|
| 2073 |
+
{
|
| 2074 |
+
"epoch": 29.466666666666665,
|
| 2075 |
+
"grad_norm": 0.17881515622138977,
|
| 2076 |
+
"learning_rate": 1.9753086419753087e-06,
|
| 2077 |
+
"loss": 0.0191,
|
| 2078 |
+
"step": 442
|
| 2079 |
+
},
|
| 2080 |
+
{
|
| 2081 |
+
"epoch": 29.6,
|
| 2082 |
+
"grad_norm": 0.15386801958084106,
|
| 2083 |
+
"learning_rate": 1.4814814814814817e-06,
|
| 2084 |
+
"loss": 0.005,
|
| 2085 |
+
"step": 444
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 29.733333333333334,
|
| 2089 |
+
"grad_norm": 0.32567164301872253,
|
| 2090 |
+
"learning_rate": 9.876543209876544e-07,
|
| 2091 |
+
"loss": 0.0077,
|
| 2092 |
+
"step": 446
|
| 2093 |
+
},
|
| 2094 |
+
{
|
| 2095 |
+
"epoch": 29.866666666666667,
|
| 2096 |
+
"grad_norm": 0.6249086260795593,
|
| 2097 |
+
"learning_rate": 4.938271604938272e-07,
|
| 2098 |
+
"loss": 0.0158,
|
| 2099 |
+
"step": 448
|
| 2100 |
+
},
|
| 2101 |
+
{
|
| 2102 |
+
"epoch": 30.0,
|
| 2103 |
+
"grad_norm": 0.24103443324565887,
|
| 2104 |
+
"learning_rate": 0.0,
|
| 2105 |
+
"loss": 0.0046,
|
| 2106 |
+
"step": 450
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 30.0,
|
| 2110 |
+
"eval_accuracy": 0.6439393939393939,
|
| 2111 |
+
"eval_f1_macro": 0.5605037390491809,
|
| 2112 |
+
"eval_f1_micro": 0.6439393939393939,
|
| 2113 |
+
"eval_f1_weighted": 0.634156085647718,
|
| 2114 |
+
"eval_loss": 1.593876838684082,
|
| 2115 |
+
"eval_precision_macro": 0.5545634920634921,
|
| 2116 |
+
"eval_precision_micro": 0.6439393939393939,
|
| 2117 |
+
"eval_precision_weighted": 0.6269465488215488,
|
| 2118 |
+
"eval_recall_macro": 0.5686545729402873,
|
| 2119 |
+
"eval_recall_micro": 0.6439393939393939,
|
| 2120 |
+
"eval_recall_weighted": 0.6439393939393939,
|
| 2121 |
+
"eval_runtime": 2.0538,
|
| 2122 |
+
"eval_samples_per_second": 64.27,
|
| 2123 |
+
"eval_steps_per_second": 2.434,
|
| 2124 |
+
"step": 450
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 30.0,
|
| 2128 |
+
"step": 450,
|
| 2129 |
+
"total_flos": 1.0740871074163507e+18,
|
| 2130 |
+
"train_loss": 0.6009381743893027,
|
| 2131 |
+
"train_runtime": 318.0836,
|
| 2132 |
+
"train_samples_per_second": 43.573,
|
| 2133 |
+
"train_steps_per_second": 1.415
|
| 2134 |
+
}
|
| 2135 |
+
],
|
| 2136 |
+
"logging_steps": 2,
|
| 2137 |
+
"max_steps": 450,
|
| 2138 |
+
"num_input_tokens_seen": 0,
|
| 2139 |
+
"num_train_epochs": 30,
|
| 2140 |
+
"save_steps": 500,
|
| 2141 |
+
"stateful_callbacks": {
|
| 2142 |
+
"TrainerControl": {
|
| 2143 |
+
"args": {
|
| 2144 |
+
"should_epoch_stop": false,
|
| 2145 |
+
"should_evaluate": false,
|
| 2146 |
+
"should_log": false,
|
| 2147 |
+
"should_save": true,
|
| 2148 |
+
"should_training_stop": true
|
| 2149 |
+
},
|
| 2150 |
+
"attributes": {}
|
| 2151 |
+
}
|
| 2152 |
+
},
|
| 2153 |
+
"total_flos": 1.0740871074163507e+18,
|
| 2154 |
+
"train_batch_size": 32,
|
| 2155 |
+
"trial_name": null,
|
| 2156 |
+
"trial_params": null
|
| 2157 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:910c7e0f885cf1c63f065cd16c8f164a2f028db680bd03a0f4461e25e8be9754
|
| 3 |
+
size 5368
|